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

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

Neuron 1146 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3253. Min Range: -5.3253

Max Act: 5.3253. Min Act: -0.1700

Data Index: 371817 (C4 (Web Text))

Max Activating Token Index: 447

Text #1

Max Range: 5.3253. Min Range: -5.3253

Max Act: 5.1378. Min Act: -0.1700

Data Index: 1010635 (C4 (Web Text))

Max Activating Token Index: 711

Text #2

Max Range: 5.3253. Min Range: -5.3253

Max Act: 5.1378. Min Act: -0.1700

Data Index: 905060 (C4 (Web Text))

Max Activating Token Index: 477

Text #3

Max Range: 5.3253. Min Range: -5.3253

Max Act: 5.1378. Min Act: -0.1700

Data Index: 548613 (C4 (Web Text))

Max Activating Token Index: 164

Text #4

Max Range: 5.3253. Min Range: -5.3253

Max Act: 5.1065. Min Act: -0.1700

Data Index: 869499 (C4 (Web Text))

Max Activating Token Index: 1003

Text #5

Max Range: 5.3253. Min Range: -5.3253

Max Act: 5.1065. Min Act: -0.1700

Data Index: 133246 (C4 (Web Text))

Max Activating Token Index: 514

Text #6

Max Range: 5.3253. Min Range: -5.3253

Max Act: 5.0440. Min Act: -0.1699

Data Index: 1209559 (C4 (Web Text))

Max Activating Token Index: 504

Text #7

Max Range: 5.3253. Min Range: -5.3253

Max Act: 4.9190. Min Act: -0.1700

Data Index: 14560 (C4 (Web Text))

Max Activating Token Index: 862

Text #8

Max Range: 5.3253. Min Range: -5.3253

Max Act: 4.9503. Min Act: -0.1699

Data Index: 52706 (C4 (Web Text))

Max Activating Token Index: 848

Text #9

Max Range: 5.3253. Min Range: -5.3253

Max Act: 4.9503. Min Act: -0.1700

Data Index: 1309770 (C4 (Web Text))

Max Activating Token Index: 528

Text #10

Max Range: 5.3253. Min Range: -5.3253

Max Act: 4.8878. Min Act: -0.1700

Data Index: 996073 (C4 (Web Text))

Max Activating Token Index: 668

Text #11

Max Range: 5.3253. Min Range: -5.3253

Max Act: 4.8565. Min Act: -0.1700

Data Index: 1211664 (C4 (Web Text))

Max Activating Token Index: 438

Text #12

Max Range: 5.3253. Min Range: -5.3253

Max Act: 4.8565. Min Act: -0.1700

Data Index: 1219745 (C4 (Web Text))

Max Activating Token Index: 527

Text #13

Max Range: 5.3253. Min Range: -5.3253

Max Act: 4.8565. Min Act: -0.1700

Data Index: 307806 (C4 (Web Text))

Max Activating Token Index: 968

Text #14

Max Range: 5.3253. Min Range: -5.3253

Max Act: 4.8565. Min Act: -0.1699

Data Index: 1080088 (C4 (Web Text))

Max Activating Token Index: 907

Text #15

Max Range: 5.3253. Min Range: -5.3253

Max Act: 4.8878. Min Act: -0.1700

Data Index: 1336103 (C4 (Web Text))

Max Activating Token Index: 620

Text #16

Max Range: 5.3253. Min Range: -5.3253

Max Act: 4.8565. Min Act: -0.1699

Data Index: 266731 (C4 (Web Text))

Max Activating Token Index: 249

Text #17

Max Range: 5.3253. Min Range: -5.3253

Max Act: 4.8878. Min Act: -0.1700

Data Index: 146337 (C4 (Web Text))

Max Activating Token Index: 459

Text #18

Max Range: 5.3253. Min Range: -5.3253

Max Act: 4.7940. Min Act: -0.1700

Data Index: 1080854 (C4 (Web Text))

Max Activating Token Index: 549

Text #19

Max Range: 5.3253. Min Range: -5.3253

Max Act: 4.8565. Min Act: -0.1700

Data Index: 1231496 (C4 (Web Text))

Max Activating Token Index: 822