Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1330 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.3430. Min Range: -5.3430

Max Act: 5.3430. Min Act: -0.1700

Data Index: 890917 (C4 (Web Text))

Max Activating Token Index: 414

Text #1

Max Range: 5.3430. Min Range: -5.3430

Max Act: 5.1868. Min Act: -0.1700

Data Index: 74404 (C4 (Web Text))

Max Activating Token Index: 468

Text #2

Max Range: 5.3430. Min Range: -5.3430

Max Act: 5.2180. Min Act: -0.1700

Data Index: 1020382 (C4 (Web Text))

Max Activating Token Index: 540

Text #3

Max Range: 5.3430. Min Range: -5.3430

Max Act: 5.0930. Min Act: -0.1700

Data Index: 687687 (C4 (Web Text))

Max Activating Token Index: 537

Text #4

Max Range: 5.3430. Min Range: -5.3430

Max Act: 5.0618. Min Act: -0.1700

Data Index: 812995 (C4 (Web Text))

Max Activating Token Index: 507

Text #5

Max Range: 5.3430. Min Range: -5.3430

Max Act: 5.0930. Min Act: -0.1700

Data Index: 1303585 (C4 (Web Text))

Max Activating Token Index: 530

Text #6

Max Range: 5.3430. Min Range: -5.3430

Max Act: 4.9680. Min Act: -0.1700

Data Index: 1042018 (C4 (Web Text))

Max Activating Token Index: 916

Text #7

Max Range: 5.3430. Min Range: -5.3430

Max Act: 4.9368. Min Act: -0.1700

Data Index: 1357245 (C4 (Web Text))

Max Activating Token Index: 813

Text #8

Max Range: 5.3430. Min Range: -5.3430

Max Act: 4.9680. Min Act: -0.1700

Data Index: 677872 (C4 (Web Text))

Max Activating Token Index: 451

Text #9

Max Range: 5.3430. Min Range: -5.3430

Max Act: 4.8743. Min Act: -0.1700

Data Index: 549634 (C4 (Web Text))

Max Activating Token Index: 12

Text #10

Max Range: 5.3430. Min Range: -5.3430

Max Act: 4.9368. Min Act: -0.1700

Data Index: 421443 (C4 (Web Text))

Max Activating Token Index: 404

Text #11

Max Range: 5.3430. Min Range: -5.3430

Max Act: 4.8743. Min Act: -0.1700

Data Index: 93553 (C4 (Web Text))

Max Activating Token Index: 813

Text #12

Max Range: 5.3430. Min Range: -5.3430

Max Act: 4.8743. Min Act: -0.1700

Data Index: 1291939 (C4 (Web Text))

Max Activating Token Index: 918

Text #13

Max Range: 5.3430. Min Range: -5.3430

Max Act: 4.8743. Min Act: -0.1700

Data Index: 1028806 (C4 (Web Text))

Max Activating Token Index: 723

Text #14

Max Range: 5.3430. Min Range: -5.3430

Max Act: 4.8743. Min Act: -0.1700

Data Index: 1314781 (C4 (Web Text))

Max Activating Token Index: 473

Text #15

Max Range: 5.3430. Min Range: -5.3430

Max Act: 4.8743. Min Act: -0.1700

Data Index: 1270774 (C4 (Web Text))

Max Activating Token Index: 804

Text #16

Max Range: 5.3430. Min Range: -5.3430

Max Act: 4.8430. Min Act: -0.1700

Data Index: 967398 (C4 (Web Text))

Max Activating Token Index: 64

Text #17

Max Range: 5.3430. Min Range: -5.3430

Max Act: 4.8430. Min Act: -0.1700

Data Index: 327435 (C4 (Web Text))

Max Activating Token Index: 867

Text #18

Max Range: 5.3430. Min Range: -5.3430

Max Act: 4.8118. Min Act: -0.1700

Data Index: 1094168 (C4 (Web Text))

Max Activating Token Index: 125

Text #19

Max Range: 5.3430. Min Range: -5.3430

Max Act: 4.8118. Min Act: -0.1700

Data Index: 1137899 (C4 (Web Text))

Max Activating Token Index: 262