Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1473 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.8167. Min Range: -5.8167

Max Act: 5.8167. Min Act: -0.1700

Data Index: 475023 (C4 (Web Text))

Max Activating Token Index: 743

Text #1

Max Range: 5.8167. Min Range: -5.8167

Max Act: 5.4417. Min Act: -0.1700

Data Index: 167522 (C4 (Web Text))

Max Activating Token Index: 352

Text #2

Max Range: 5.8167. Min Range: -5.8167

Max Act: 5.3792. Min Act: -0.1700

Data Index: 1170397 (C4 (Web Text))

Max Activating Token Index: 780

Text #3

Max Range: 5.8167. Min Range: -5.8167

Max Act: 5.3480. Min Act: -0.1700

Data Index: 443258 (C4 (Web Text))

Max Activating Token Index: 691

Text #4

Max Range: 5.8167. Min Range: -5.8167

Max Act: 5.3167. Min Act: -0.1700

Data Index: 222929 (C4 (Web Text))

Max Activating Token Index: 558

Text #5

Max Range: 5.8167. Min Range: -5.8167

Max Act: 5.3167. Min Act: -0.1700

Data Index: 959373 (C4 (Web Text))

Max Activating Token Index: 991

Text #6

Max Range: 5.8167. Min Range: -5.8167

Max Act: 5.3792. Min Act: -0.1700

Data Index: 872756 (C4 (Web Text))

Max Activating Token Index: 247

Text #7

Max Range: 5.8167. Min Range: -5.8167

Max Act: 5.3480. Min Act: -0.1700

Data Index: 441252 (C4 (Web Text))

Max Activating Token Index: 996

Text #8

Max Range: 5.8167. Min Range: -5.8167

Max Act: 5.2230. Min Act: -0.1700

Data Index: 886597 (C4 (Web Text))

Max Activating Token Index: 1008

Text #9

Max Range: 5.8167. Min Range: -5.8167

Max Act: 5.2230. Min Act: -0.1700

Data Index: 904904 (C4 (Web Text))

Max Activating Token Index: 555

Text #10

Max Range: 5.8167. Min Range: -5.8167

Max Act: 5.0980. Min Act: -0.1700

Data Index: 609562 (C4 (Web Text))

Max Activating Token Index: 890

Text #11

Max Range: 5.8167. Min Range: -5.8167

Max Act: 5.1917. Min Act: -0.1700

Data Index: 1222040 (C4 (Web Text))

Max Activating Token Index: 633

Text #12

Max Range: 5.8167. Min Range: -5.8167

Max Act: 5.1605. Min Act: -0.1700

Data Index: 1131442 (C4 (Web Text))

Max Activating Token Index: 639

Text #13

Max Range: 5.8167. Min Range: -5.8167

Max Act: 5.1605. Min Act: -0.1700

Data Index: 440167 (C4 (Web Text))

Max Activating Token Index: 325

Text #14

Max Range: 5.8167. Min Range: -5.8167

Max Act: 5.1292. Min Act: -0.1700

Data Index: 564781 (C4 (Web Text))

Max Activating Token Index: 735

Text #15

Max Range: 5.8167. Min Range: -5.8167

Max Act: 5.0667. Min Act: -0.1700

Data Index: 765846 (C4 (Web Text))

Max Activating Token Index: 653

Text #16

Max Range: 5.8167. Min Range: -5.8167

Max Act: 5.0667. Min Act: -0.1700

Data Index: 154469 (C4 (Web Text))

Max Activating Token Index: 320

Text #17

Max Range: 5.8167. Min Range: -5.8167

Max Act: 5.0980. Min Act: -0.1700

Data Index: 1112884 (C4 (Web Text))

Max Activating Token Index: 552

Text #18

Max Range: 5.8167. Min Range: -5.8167

Max Act: 5.0667. Min Act: -0.1700

Data Index: 112860 (C4 (Web Text))

Max Activating Token Index: 383

Text #19

Max Range: 5.8167. Min Range: -5.8167

Max Act: 5.0355. Min Act: -0.1700

Data Index: 318712 (C4 (Web Text))

Max Activating Token Index: 681