< Prev | Home | Model | Random | Next >

Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 425 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')



Text #0

Max Range: 2.6267. Min Range: -2.6267

Max Act: 2.6267. Min Act: -0.1700

Data Index: 416027 (C4 (Web Text))

Max Activating Token Index: 986

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.6267. Min Range: -2.6267

Max Act: 2.5623. Min Act: -0.1700

Data Index: 175046 (C4 (Web Text))

Max Activating Token Index: 9

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.6267. Min Range: -2.6267

Max Act: 2.5462. Min Act: -0.1700

Data Index: 457807 (C4 (Web Text))

Max Activating Token Index: 560

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.6267. Min Range: -2.6267

Max Act: 2.5139. Min Act: -0.1700

Data Index: 1311390 (C4 (Web Text))

Max Activating Token Index: 37

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.6267. Min Range: -2.6267

Max Act: 2.4815. Min Act: -0.1700

Data Index: 1270337 (C4 (Web Text))

Max Activating Token Index: 601

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.6267. Min Range: -2.6267

Max Act: 2.4815. Min Act: -0.1700

Data Index: 838120 (C4 (Web Text))

Max Activating Token Index: 827

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.6267. Min Range: -2.6267

Max Act: 2.4815. Min Act: -0.1700

Data Index: 1027903 (C4 (Web Text))

Max Activating Token Index: 47

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.6267. Min Range: -2.6267

Max Act: 2.4327. Min Act: -0.1700

Data Index: 1646024 (Python Code)

Max Activating Token Index: 1007

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.6267. Min Range: -2.6267

Max Act: 2.4652. Min Act: -0.1700

Data Index: 476590 (C4 (Web Text))

Max Activating Token Index: 846

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.6267. Min Range: -2.6267

Max Act: 2.4490. Min Act: -0.1700

Data Index: 377800 (C4 (Web Text))

Max Activating Token Index: 899

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.6267. Min Range: -2.6267

Max Act: 2.4327. Min Act: -0.1700

Data Index: 753076 (C4 (Web Text))

Max Activating Token Index: 408

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.6267. Min Range: -2.6267

Max Act: 2.4165. Min Act: -0.1700

Data Index: 531547 (C4 (Web Text))

Max Activating Token Index: 802

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.6267. Min Range: -2.6267

Max Act: 2.4327. Min Act: -0.1700

Data Index: 663558 (C4 (Web Text))

Max Activating Token Index: 384

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.6267. Min Range: -2.6267

Max Act: 2.4002. Min Act: -0.1700

Data Index: 625340 (C4 (Web Text))

Max Activating Token Index: 383

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.6267. Min Range: -2.6267

Max Act: 2.3838. Min Act: -0.1700

Data Index: 1179752 (C4 (Web Text))

Max Activating Token Index: 480

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.6267. Min Range: -2.6267

Max Act: 2.4002. Min Act: -0.1700

Data Index: 390905 (C4 (Web Text))

Max Activating Token Index: 626

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.6267. Min Range: -2.6267

Max Act: 2.4002. Min Act: -0.1700

Data Index: 1595989 (Python Code)

Max Activating Token Index: 35

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.6267. Min Range: -2.6267

Max Act: 2.3675. Min Act: -0.1700

Data Index: 555233 (C4 (Web Text))

Max Activating Token Index: 878

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.6267. Min Range: -2.6267

Max Act: 2.3838. Min Act: -0.1700

Data Index: 146961 (C4 (Web Text))

Max Activating Token Index: 792

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.6267. Min Range: -2.6267

Max Act: 2.3838. Min Act: -0.1700

Data Index: 872173 (C4 (Web Text))

Max Activating Token Index: 895

Click toggle to see full text

Truncated

Full Text #19