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

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

Neuron 454 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: 5.2939. Min Range: -5.2939

Max Act: 5.2939. Min Act: -0.1700

Data Index: 423527 (C4 (Web Text))

Max Activating Token Index: 513

Text #1

Max Range: 5.2939. Min Range: -5.2939

Max Act: 5.2627. Min Act: -0.1700

Data Index: 1117115 (C4 (Web Text))

Max Activating Token Index: 286

Text #2

Max Range: 5.2939. Min Range: -5.2939

Max Act: 5.1377. Min Act: -0.1700

Data Index: 978579 (C4 (Web Text))

Max Activating Token Index: 688

Text #3

Max Range: 5.2939. Min Range: -5.2939

Max Act: 5.0439. Min Act: -0.1700

Data Index: 1202989 (C4 (Web Text))

Max Activating Token Index: 558

Text #4

Max Range: 5.2939. Min Range: -5.2939

Max Act: 5.0439. Min Act: -0.1700

Data Index: 988220 (C4 (Web Text))

Max Activating Token Index: 478

Text #5

Max Range: 5.2939. Min Range: -5.2939

Max Act: 5.0127. Min Act: -0.1700

Data Index: 698288 (C4 (Web Text))

Max Activating Token Index: 814

Text #6

Max Range: 5.2939. Min Range: -5.2939

Max Act: 5.0127. Min Act: -0.1700

Data Index: 64382 (C4 (Web Text))

Max Activating Token Index: 305

Text #7

Max Range: 5.2939. Min Range: -5.2939

Max Act: 5.0439. Min Act: -0.1700

Data Index: 1337677 (C4 (Web Text))

Max Activating Token Index: 148

Text #8

Max Range: 5.2939. Min Range: -5.2939

Max Act: 4.9502. Min Act: -0.1700

Data Index: 1411942 (Python Code)

Max Activating Token Index: 593

Text #9

Max Range: 5.2939. Min Range: -5.2939

Max Act: 4.8564. Min Act: -0.1700

Data Index: 1274679 (C4 (Web Text))

Max Activating Token Index: 874

Text #10

Max Range: 5.2939. Min Range: -5.2939

Max Act: 4.9189. Min Act: -0.1700

Data Index: 712138 (C4 (Web Text))

Max Activating Token Index: 210

Text #11

Max Range: 5.2939. Min Range: -5.2939

Max Act: 4.9502. Min Act: -0.1700

Data Index: 780676 (C4 (Web Text))

Max Activating Token Index: 470

Text #12

Max Range: 5.2939. Min Range: -5.2939

Max Act: 4.9189. Min Act: -0.1700

Data Index: 375218 (C4 (Web Text))

Max Activating Token Index: 363

Text #13

Max Range: 5.2939. Min Range: -5.2939

Max Act: 4.9502. Min Act: -0.1700

Data Index: 1042570 (C4 (Web Text))

Max Activating Token Index: 52

Text #14

Max Range: 5.2939. Min Range: -5.2939

Max Act: 4.8564. Min Act: -0.1700

Data Index: 502394 (C4 (Web Text))

Max Activating Token Index: 433

Text #15

Max Range: 5.2939. Min Range: -5.2939

Max Act: 4.9189. Min Act: -0.1700

Data Index: 710357 (C4 (Web Text))

Max Activating Token Index: 825

Text #16

Max Range: 5.2939. Min Range: -5.2939

Max Act: 4.8252. Min Act: -0.1700

Data Index: 357485 (C4 (Web Text))

Max Activating Token Index: 17

Text #17

Max Range: 5.2939. Min Range: -5.2939

Max Act: 4.8877. Min Act: -0.1700

Data Index: 1017408 (C4 (Web Text))

Max Activating Token Index: 735

Text #18

Max Range: 5.2939. Min Range: -5.2939

Max Act: 4.9814. Min Act: -0.1700

Data Index: 923436 (C4 (Web Text))

Max Activating Token Index: 248

Text #19

Max Range: 5.2939. Min Range: -5.2939

Max Act: 4.8877. Min Act: -0.1700

Data Index: 506582 (C4 (Web Text))

Max Activating Token Index: 707