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

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

Neuron 354 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: 5.9117. Min Range: -5.9117

Max Act: 5.7867. Min Act: -0.1700

Data Index: 1078016 (C4 (Web Text))

Max Activating Token Index: 986

Text #1

Max Range: 5.9117. Min Range: -5.9117

Max Act: 5.9117. Min Act: -0.1700

Data Index: 220643 (C4 (Web Text))

Max Activating Token Index: 774

Text #2

Max Range: 5.9117. Min Range: -5.9117

Max Act: 5.8804. Min Act: -0.1700

Data Index: 1202858 (C4 (Web Text))

Max Activating Token Index: 1006

Text #3

Max Range: 5.9117. Min Range: -5.9117

Max Act: 5.8492. Min Act: -0.1700

Data Index: 244449 (C4 (Web Text))

Max Activating Token Index: 662

Text #4

Max Range: 5.9117. Min Range: -5.9117

Max Act: 5.7554. Min Act: -0.1700

Data Index: 970585 (C4 (Web Text))

Max Activating Token Index: 877

Text #5

Max Range: 5.9117. Min Range: -5.9117

Max Act: 5.7242. Min Act: -0.1700

Data Index: 758734 (C4 (Web Text))

Max Activating Token Index: 942

Text #6

Max Range: 5.9117. Min Range: -5.9117

Max Act: 5.7867. Min Act: -0.1700

Data Index: 378869 (C4 (Web Text))

Max Activating Token Index: 117

Text #7

Max Range: 5.9117. Min Range: -5.9117

Max Act: 5.7554. Min Act: -0.1700

Data Index: 365722 (C4 (Web Text))

Max Activating Token Index: 615

Text #8

Max Range: 5.9117. Min Range: -5.9117

Max Act: 5.8492. Min Act: -0.1700

Data Index: 842645 (C4 (Web Text))

Max Activating Token Index: 239

Text #9

Max Range: 5.9117. Min Range: -5.9117

Max Act: 5.7867. Min Act: -0.1700

Data Index: 483388 (C4 (Web Text))

Max Activating Token Index: 230

Text #10

Max Range: 5.9117. Min Range: -5.9117

Max Act: 5.7867. Min Act: -0.1700

Data Index: 713569 (C4 (Web Text))

Max Activating Token Index: 923

Text #11

Max Range: 5.9117. Min Range: -5.9117

Max Act: 5.8179. Min Act: -0.1700

Data Index: 1271516 (C4 (Web Text))

Max Activating Token Index: 128

Text #12

Max Range: 5.9117. Min Range: -5.9117

Max Act: 5.7242. Min Act: -0.1700

Data Index: 1061824 (C4 (Web Text))

Max Activating Token Index: 329

Text #13

Max Range: 5.9117. Min Range: -5.9117

Max Act: 5.7554. Min Act: -0.1700

Data Index: 919398 (C4 (Web Text))

Max Activating Token Index: 919

Text #14

Max Range: 5.9117. Min Range: -5.9117

Max Act: 5.7242. Min Act: -0.1700

Data Index: 1358199 (C4 (Web Text))

Max Activating Token Index: 389

Text #15

Max Range: 5.9117. Min Range: -5.9117

Max Act: 5.7242. Min Act: -0.1700

Data Index: 1131831 (C4 (Web Text))

Max Activating Token Index: 991

Text #16

Max Range: 5.9117. Min Range: -5.9117

Max Act: 5.7242. Min Act: -0.1700

Data Index: 629850 (C4 (Web Text))

Max Activating Token Index: 508

Text #17

Max Range: 5.9117. Min Range: -5.9117

Max Act: 5.7867. Min Act: -0.1700

Data Index: 607857 (C4 (Web Text))

Max Activating Token Index: 841

Text #18

Max Range: 5.9117. Min Range: -5.9117

Max Act: 5.6929. Min Act: -0.1700

Data Index: 593067 (C4 (Web Text))

Max Activating Token Index: 256

Text #19

Max Range: 5.9117. Min Range: -5.9117

Max Act: 5.7554. Min Act: -0.1700

Data Index: 349567 (C4 (Web Text))

Max Activating Token Index: 815