Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2108 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 5.1355. Min Range: -5.1355

Max Act: 4.9695. Min Act: -0.0000

Data Index: 55836 (C4 (Web Text))

Max Activating Token Index: 141

Text #1

Max Range: 5.1355. Min Range: -5.1355

Max Act: 5.1355. Min Act: -0.0000

Data Index: 822391 (C4 (Web Text))

Max Activating Token Index: 172

Text #2

Max Range: 5.1355. Min Range: -5.1355

Max Act: 4.9004. Min Act: -0.0000

Data Index: 490186 (C4 (Web Text))

Max Activating Token Index: 55

Text #3

Max Range: 5.1355. Min Range: -5.1355

Max Act: 4.7329. Min Act: -0.0000

Data Index: 419643 (C4 (Web Text))

Max Activating Token Index: 698

Text #4

Max Range: 5.1355. Min Range: -5.1355

Max Act: 4.8283. Min Act: -0.0000

Data Index: 312941 (C4 (Web Text))

Max Activating Token Index: 144

Text #5

Max Range: 5.1355. Min Range: -5.1355

Max Act: 4.6851. Min Act: -0.0000

Data Index: 1150940 (C4 (Web Text))

Max Activating Token Index: 667

Text #6

Max Range: 5.1355. Min Range: -5.1355

Max Act: 4.4294. Min Act: -0.0000

Data Index: 1130936 (C4 (Web Text))

Max Activating Token Index: 196

Text #7

Max Range: 5.1355. Min Range: -5.1355

Max Act: 4.6012. Min Act: -0.0000

Data Index: 1289385 (C4 (Web Text))

Max Activating Token Index: 339

Text #8

Max Range: 5.1355. Min Range: -5.1355

Max Act: 4.5126. Min Act: -0.0000

Data Index: 403781 (C4 (Web Text))

Max Activating Token Index: 107

Text #9

Max Range: 5.1355. Min Range: -5.1355

Max Act: 4.5027. Min Act: -0.0000

Data Index: 1031724 (C4 (Web Text))

Max Activating Token Index: 772

Text #10

Max Range: 5.1355. Min Range: -5.1355

Max Act: 4.4771. Min Act: -0.0000

Data Index: 649346 (C4 (Web Text))

Max Activating Token Index: 360

Text #11

Max Range: 5.1355. Min Range: -5.1355

Max Act: 4.4479. Min Act: -0.0000

Data Index: 701693 (C4 (Web Text))

Max Activating Token Index: 359

Text #12

Max Range: 5.1355. Min Range: -5.1355

Max Act: 4.6233. Min Act: -0.0000

Data Index: 6941 (C4 (Web Text))

Max Activating Token Index: 604

Text #13

Max Range: 5.1355. Min Range: -5.1355

Max Act: 4.3951. Min Act: -0.0000

Data Index: 677776 (C4 (Web Text))

Max Activating Token Index: 414

Text #14

Max Range: 5.1355. Min Range: -5.1355

Max Act: 4.3983. Min Act: -0.0000

Data Index: 1264307 (C4 (Web Text))

Max Activating Token Index: 68

Text #15

Max Range: 5.1355. Min Range: -5.1355

Max Act: 4.3694. Min Act: -0.0000

Data Index: 143727 (C4 (Web Text))

Max Activating Token Index: 895

Text #16

Max Range: 5.1355. Min Range: -5.1355

Max Act: 4.2916. Min Act: -0.0000

Data Index: 742520 (C4 (Web Text))

Max Activating Token Index: 698

Text #17

Max Range: 5.1355. Min Range: -5.1355

Max Act: 4.1166. Min Act: -0.0000

Data Index: 536787 (C4 (Web Text))

Max Activating Token Index: 1015

Text #18

Max Range: 5.1355. Min Range: -5.1355

Max Act: 4.4542. Min Act: -0.0000

Data Index: 495592 (C4 (Web Text))

Max Activating Token Index: 179

Text #19

Max Range: 5.1355. Min Range: -5.1355

Max Act: 4.2163. Min Act: -0.0000

Data Index: 976160 (C4 (Web Text))

Max Activating Token Index: 97