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

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

Neuron 1745 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: 3.6227. Min Range: -3.6227

Max Act: 3.6227. Min Act: -0.1699

Data Index: 850238 (C4 (Web Text))

Max Activating Token Index: 76

Text #1

Max Range: 3.6227. Min Range: -3.6227

Max Act: 3.5601. Min Act: -0.1700

Data Index: 487257 (C4 (Web Text))

Max Activating Token Index: 808

Text #2

Max Range: 3.6227. Min Range: -3.6227

Max Act: 3.5287. Min Act: -0.1700

Data Index: 237562 (C4 (Web Text))

Max Activating Token Index: 568

Text #3

Max Range: 3.6227. Min Range: -3.6227

Max Act: 3.4661. Min Act: -0.1700

Data Index: 924904 (C4 (Web Text))

Max Activating Token Index: 428

Text #4

Max Range: 3.6227. Min Range: -3.6227

Max Act: 3.3406. Min Act: -0.1700

Data Index: 1334940 (C4 (Web Text))

Max Activating Token Index: 919

Text #5

Max Range: 3.6227. Min Range: -3.6227

Max Act: 3.3092. Min Act: -0.1700

Data Index: 561380 (C4 (Web Text))

Max Activating Token Index: 378

Text #6

Max Range: 3.6227. Min Range: -3.6227

Max Act: 3.2463. Min Act: -0.1700

Data Index: 971176 (C4 (Web Text))

Max Activating Token Index: 255

Text #7

Max Range: 3.6227. Min Range: -3.6227

Max Act: 3.2778. Min Act: -0.1700

Data Index: 59854 (C4 (Web Text))

Max Activating Token Index: 402

Text #8

Max Range: 3.6227. Min Range: -3.6227

Max Act: 3.2778. Min Act: -0.1700

Data Index: 48723 (C4 (Web Text))

Max Activating Token Index: 544

Text #9

Max Range: 3.6227. Min Range: -3.6227

Max Act: 3.2463. Min Act: -0.1700

Data Index: 1224916 (C4 (Web Text))

Max Activating Token Index: 570

Text #10

Max Range: 3.6227. Min Range: -3.6227

Max Act: 3.2149. Min Act: -0.1700

Data Index: 33234 (C4 (Web Text))

Max Activating Token Index: 81

Text #11

Max Range: 3.6227. Min Range: -3.6227

Max Act: 3.1834. Min Act: -0.1700

Data Index: 179733 (C4 (Web Text))

Max Activating Token Index: 114

Text #12

Max Range: 3.6227. Min Range: -3.6227

Max Act: 3.1519. Min Act: -0.1700

Data Index: 272798 (C4 (Web Text))

Max Activating Token Index: 836

Text #13

Max Range: 3.6227. Min Range: -3.6227

Max Act: 3.1204. Min Act: -0.1700

Data Index: 1137793 (C4 (Web Text))

Max Activating Token Index: 798

Text #14

Max Range: 3.6227. Min Range: -3.6227

Max Act: 3.1519. Min Act: -0.1700

Data Index: 29337 (C4 (Web Text))

Max Activating Token Index: 9

Text #15

Max Range: 3.6227. Min Range: -3.6227

Max Act: 3.1204. Min Act: -0.1700

Data Index: 698544 (C4 (Web Text))

Max Activating Token Index: 574

Text #16

Max Range: 3.6227. Min Range: -3.6227

Max Act: 3.1204. Min Act: -0.1700

Data Index: 470053 (C4 (Web Text))

Max Activating Token Index: 515

Text #17

Max Range: 3.6227. Min Range: -3.6227

Max Act: 3.1204. Min Act: -0.1700

Data Index: 827733 (C4 (Web Text))

Max Activating Token Index: 501

Text #18

Max Range: 3.6227. Min Range: -3.6227

Max Act: 3.1519. Min Act: -0.1700

Data Index: 388463 (C4 (Web Text))

Max Activating Token Index: 788

Text #19

Max Range: 3.6227. Min Range: -3.6227

Max Act: 3.1204. Min Act: -0.1700

Data Index: 90617 (C4 (Web Text))

Max Activating Token Index: 769