< Prev | Home | Model | Random | Next >

Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 986 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')



Text #0

Max Range: 2.2907. Min Range: -2.2907

Max Act: 2.2907. Min Act: -0.1700

Data Index: 1562242 (Python Code)

Max Activating Token Index: 5

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.2907. Min Range: -2.2907

Max Act: 2.2412. Min Act: -0.1700

Data Index: 200214 (C4 (Web Text))

Max Activating Token Index: 985

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.2907. Min Range: -2.2907

Max Act: 2.2412. Min Act: -0.1700

Data Index: 1225588 (C4 (Web Text))

Max Activating Token Index: 504

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.2907. Min Range: -2.2907

Max Act: 2.2247. Min Act: -0.1700

Data Index: 506658 (C4 (Web Text))

Max Activating Token Index: 283

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.2907. Min Range: -2.2907

Max Act: 2.2247. Min Act: -0.1700

Data Index: 1437826 (Python Code)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.2907. Min Range: -2.2907

Max Act: 2.2081. Min Act: -0.1700

Data Index: 476571 (C4 (Web Text))

Max Activating Token Index: 70

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.2907. Min Range: -2.2907

Max Act: 2.2081. Min Act: -0.1700

Data Index: 1136339 (C4 (Web Text))

Max Activating Token Index: 305

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.2907. Min Range: -2.2907

Max Act: 2.1749. Min Act: -0.1700

Data Index: 1585929 (Python Code)

Max Activating Token Index: 869

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.2907. Min Range: -2.2907

Max Act: 2.1915. Min Act: -0.1700

Data Index: 1194123 (C4 (Web Text))

Max Activating Token Index: 363

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.2907. Min Range: -2.2907

Max Act: 2.1583. Min Act: -0.1700

Data Index: 588436 (C4 (Web Text))

Max Activating Token Index: 176

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.2907. Min Range: -2.2907

Max Act: 2.1749. Min Act: -0.1700

Data Index: 417949 (C4 (Web Text))

Max Activating Token Index: 305

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.2907. Min Range: -2.2907

Max Act: 2.1749. Min Act: -0.1700

Data Index: 750149 (C4 (Web Text))

Max Activating Token Index: 614

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.2907. Min Range: -2.2907

Max Act: 2.1915. Min Act: -0.1700

Data Index: 1238252 (C4 (Web Text))

Max Activating Token Index: 173

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.2907. Min Range: -2.2907

Max Act: 2.1749. Min Act: -0.1700

Data Index: 902953 (C4 (Web Text))

Max Activating Token Index: 655

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.2907. Min Range: -2.2907

Max Act: 2.1749. Min Act: -0.1700

Data Index: 1265986 (C4 (Web Text))

Max Activating Token Index: 910

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.2907. Min Range: -2.2907

Max Act: 2.1749. Min Act: -0.1700

Data Index: 1281979 (C4 (Web Text))

Max Activating Token Index: 322

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.2907. Min Range: -2.2907

Max Act: 2.1749. Min Act: -0.1700

Data Index: 266647 (C4 (Web Text))

Max Activating Token Index: 87

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.2907. Min Range: -2.2907

Max Act: 2.1749. Min Act: -0.1700

Data Index: 958706 (C4 (Web Text))

Max Activating Token Index: 33

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.2907. Min Range: -2.2907

Max Act: 2.1749. Min Act: -0.1700

Data Index: 481875 (C4 (Web Text))

Max Activating Token Index: 640

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.2907. Min Range: -2.2907

Max Act: 2.1749. Min Act: -0.1700

Data Index: 1332861 (C4 (Web Text))

Max Activating Token Index: 144

Click toggle to see full text

Truncated

Full Text #19