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

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

Neuron 1817 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2798. Min Range: -5.2798

Max Act: 5.2798. Min Act: -0.1700

Data Index: 932665 (C4 (Web Text))

Max Activating Token Index: 167

Text #1

Max Range: 5.2798. Min Range: -5.2798

Max Act: 4.9204. Min Act: -0.1700

Data Index: 519023 (C4 (Web Text))

Max Activating Token Index: 928

Text #2

Max Range: 5.2798. Min Range: -5.2798

Max Act: 4.8423. Min Act: -0.1700

Data Index: 275728 (C4 (Web Text))

Max Activating Token Index: 37

Text #3

Max Range: 5.2798. Min Range: -5.2798

Max Act: 4.8892. Min Act: -0.1700

Data Index: 1044767 (C4 (Web Text))

Max Activating Token Index: 366

Text #4

Max Range: 5.2798. Min Range: -5.2798

Max Act: 4.7798. Min Act: -0.1700

Data Index: 129520 (C4 (Web Text))

Max Activating Token Index: 790

Text #5

Max Range: 5.2798. Min Range: -5.2798

Max Act: 4.8423. Min Act: -0.1700

Data Index: 937255 (C4 (Web Text))

Max Activating Token Index: 103

Text #6

Max Range: 5.2798. Min Range: -5.2798

Max Act: 4.8111. Min Act: -0.1700

Data Index: 801671 (C4 (Web Text))

Max Activating Token Index: 610

Text #7

Max Range: 5.2798. Min Range: -5.2798

Max Act: 4.7486. Min Act: -0.1700

Data Index: 831813 (C4 (Web Text))

Max Activating Token Index: 941

Text #8

Max Range: 5.2798. Min Range: -5.2798

Max Act: 4.8111. Min Act: -0.1700

Data Index: 165580 (C4 (Web Text))

Max Activating Token Index: 277

Text #9

Max Range: 5.2798. Min Range: -5.2798

Max Act: 4.6548. Min Act: -0.1700

Data Index: 1020337 (C4 (Web Text))

Max Activating Token Index: 207

Text #10

Max Range: 5.2798. Min Range: -5.2798

Max Act: 4.6548. Min Act: -0.1700

Data Index: 159596 (C4 (Web Text))

Max Activating Token Index: 71

Text #11

Max Range: 5.2798. Min Range: -5.2798

Max Act: 4.6548. Min Act: -0.1700

Data Index: 333230 (C4 (Web Text))

Max Activating Token Index: 932

Text #12

Max Range: 5.2798. Min Range: -5.2798

Max Act: 4.6236. Min Act: -0.1700

Data Index: 887937 (C4 (Web Text))

Max Activating Token Index: 677

Text #13

Max Range: 5.2798. Min Range: -5.2798

Max Act: 4.5923. Min Act: -0.1700

Data Index: 754136 (C4 (Web Text))

Max Activating Token Index: 127

Text #14

Max Range: 5.2798. Min Range: -5.2798

Max Act: 4.6236. Min Act: -0.1700

Data Index: 92571 (C4 (Web Text))

Max Activating Token Index: 774

Text #15

Max Range: 5.2798. Min Range: -5.2798

Max Act: 4.6236. Min Act: -0.1700

Data Index: 60268 (C4 (Web Text))

Max Activating Token Index: 766

Text #16

Max Range: 5.2798. Min Range: -5.2798

Max Act: 4.5611. Min Act: -0.1700

Data Index: 501620 (C4 (Web Text))

Max Activating Token Index: 261

Text #17

Max Range: 5.2798. Min Range: -5.2798

Max Act: 4.5923. Min Act: -0.1700

Data Index: 1273290 (C4 (Web Text))

Max Activating Token Index: 316

Text #18

Max Range: 5.2798. Min Range: -5.2798

Max Act: 4.5454. Min Act: -0.1700

Data Index: 810701 (C4 (Web Text))

Max Activating Token Index: 832

Text #19

Max Range: 5.2798. Min Range: -5.2798

Max Act: 4.5298. Min Act: -0.1700

Data Index: 337862 (C4 (Web Text))

Max Activating Token Index: 983