< Prev | Home | Model | Random | Next >

Model: GELU Model: 2 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1242 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')



Text #0

Max Range: 3.0146. Min Range: -3.0146

Max Act: 3.0146. Min Act: -0.1700

Data Index: 155020 (C4 (Web Text))

Max Activating Token Index: 167

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.0146. Min Range: -3.0146

Max Act: 2.8880. Min Act: -0.1700

Data Index: 910394 (C4 (Web Text))

Max Activating Token Index: 690

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.0146. Min Range: -3.0146

Max Act: 2.7128. Min Act: -0.1700

Data Index: 638068 (C4 (Web Text))

Max Activating Token Index: 198

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.0146. Min Range: -3.0146

Max Act: 2.6968. Min Act: -0.1700

Data Index: 1198033 (C4 (Web Text))

Max Activating Token Index: 495

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.0146. Min Range: -3.0146

Max Act: 2.6968. Min Act: -0.1700

Data Index: 1136386 (C4 (Web Text))

Max Activating Token Index: 263

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.0146. Min Range: -3.0146

Max Act: 2.6487. Min Act: -0.1700

Data Index: 1397762 (Python Code)

Max Activating Token Index: 102

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.0146. Min Range: -3.0146

Max Act: 2.6166. Min Act: -0.1700

Data Index: 1342053 (C4 (Web Text))

Max Activating Token Index: 381

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.0146. Min Range: -3.0146

Max Act: 2.6166. Min Act: -0.1700

Data Index: 1392762 (Python Code)

Max Activating Token Index: 638

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.0146. Min Range: -3.0146

Max Act: 2.5844. Min Act: -0.1700

Data Index: 1266561 (C4 (Web Text))

Max Activating Token Index: 108

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.0146. Min Range: -3.0146

Max Act: 2.5683. Min Act: -0.1700

Data Index: 289981 (C4 (Web Text))

Max Activating Token Index: 602

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.0146. Min Range: -3.0146

Max Act: 2.5844. Min Act: -0.1700

Data Index: 1361328 (Python Code)

Max Activating Token Index: 381

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.0146. Min Range: -3.0146

Max Act: 2.5683. Min Act: -0.1700

Data Index: 324712 (C4 (Web Text))

Max Activating Token Index: 636

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.0146. Min Range: -3.0146

Max Act: 2.5521. Min Act: -0.1700

Data Index: 141178 (C4 (Web Text))

Max Activating Token Index: 248

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.0146. Min Range: -3.0146

Max Act: 2.5521. Min Act: -0.1700

Data Index: 745845 (C4 (Web Text))

Max Activating Token Index: 312

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.0146. Min Range: -3.0146

Max Act: 2.5198. Min Act: -0.1700

Data Index: 1279782 (C4 (Web Text))

Max Activating Token Index: 737

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.0146. Min Range: -3.0146

Max Act: 2.5198. Min Act: -0.1700

Data Index: 907974 (C4 (Web Text))

Max Activating Token Index: 75

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.0146. Min Range: -3.0146

Max Act: 2.5036. Min Act: -0.1700

Data Index: 101206 (C4 (Web Text))

Max Activating Token Index: 562

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.0146. Min Range: -3.0146

Max Act: 2.5036. Min Act: -0.1700

Data Index: 467279 (C4 (Web Text))

Max Activating Token Index: 232

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.0146. Min Range: -3.0146

Max Act: 2.4874. Min Act: -0.1700

Data Index: 536272 (C4 (Web Text))

Max Activating Token Index: 103

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.0146. Min Range: -3.0146

Max Act: 2.4874. Min Act: -0.1700

Data Index: 909027 (C4 (Web Text))

Max Activating Token Index: 81

Click toggle to see full text

Truncated

Full Text #19