Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2090 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4207. Min Range: -0.4207

Max Act: 0.4114. Min Act: -0.0001

Data Index: 1126874 (C4 (Web Text))

Max Activating Token Index: 740

Text #1

Max Range: 0.4207. Min Range: -0.4207

Max Act: 0.4098. Min Act: -0.0001

Data Index: 864740 (C4 (Web Text))

Max Activating Token Index: 782

Text #2

Max Range: 0.4207. Min Range: -0.4207

Max Act: 0.4207. Min Act: -0.0001

Data Index: 223595 (C4 (Web Text))

Max Activating Token Index: 725

Text #3

Max Range: 0.4207. Min Range: -0.4207

Max Act: 0.3477. Min Act: -0.0001

Data Index: 855054 (C4 (Web Text))

Max Activating Token Index: 964

Text #4

Max Range: 0.4207. Min Range: -0.4207

Max Act: 0.3347. Min Act: -0.0001

Data Index: 361891 (C4 (Web Text))

Max Activating Token Index: 261

Text #5

Max Range: 0.4207. Min Range: -0.4207

Max Act: 0.3582. Min Act: -0.0001

Data Index: 988091 (C4 (Web Text))

Max Activating Token Index: 723

Text #6

Max Range: 0.4207. Min Range: -0.4207

Max Act: 0.3317. Min Act: -0.0001

Data Index: 551488 (C4 (Web Text))

Max Activating Token Index: 894

Text #7

Max Range: 0.4207. Min Range: -0.4207

Max Act: 0.3333. Min Act: -0.0001

Data Index: 868833 (C4 (Web Text))

Max Activating Token Index: 675

Text #8

Max Range: 0.4207. Min Range: -0.4207

Max Act: 0.3391. Min Act: -0.0001

Data Index: 379222 (C4 (Web Text))

Max Activating Token Index: 119

Text #9

Max Range: 0.4207. Min Range: -0.4207

Max Act: 0.3292. Min Act: -0.0001

Data Index: 568645 (C4 (Web Text))

Max Activating Token Index: 788

Text #10

Max Range: 0.4207. Min Range: -0.4207

Max Act: 0.3144. Min Act: -0.0001

Data Index: 286056 (C4 (Web Text))

Max Activating Token Index: 710

Text #11

Max Range: 0.4207. Min Range: -0.4207

Max Act: 0.2926. Min Act: -0.0001

Data Index: 490875 (C4 (Web Text))

Max Activating Token Index: 700

Text #12

Max Range: 0.4207. Min Range: -0.4207

Max Act: 0.3205. Min Act: -0.0001

Data Index: 1276146 (C4 (Web Text))

Max Activating Token Index: 482

Text #13

Max Range: 0.4207. Min Range: -0.4207

Max Act: 0.2968. Min Act: -0.0000

Data Index: 450991 (C4 (Web Text))

Max Activating Token Index: 910

Text #14

Max Range: 0.4207. Min Range: -0.4207

Max Act: 0.3059. Min Act: -0.0001

Data Index: 703770 (C4 (Web Text))

Max Activating Token Index: 847

Text #15

Max Range: 0.4207. Min Range: -0.4207

Max Act: 0.3281. Min Act: -0.0001

Data Index: 197436 (C4 (Web Text))

Max Activating Token Index: 397

Text #16

Max Range: 0.4207. Min Range: -0.4207

Max Act: 0.3073. Min Act: -0.0001

Data Index: 1207101 (C4 (Web Text))

Max Activating Token Index: 453

Text #17

Max Range: 0.4207. Min Range: -0.4207

Max Act: 0.3065. Min Act: -0.0001

Data Index: 902369 (C4 (Web Text))

Max Activating Token Index: 635

Text #18

Max Range: 0.4207. Min Range: -0.4207

Max Act: 0.3115. Min Act: -0.0001

Data Index: 1020040 (C4 (Web Text))

Max Activating Token Index: 264

Text #19

Max Range: 0.4207. Min Range: -0.4207

Max Act: 0.2781. Min Act: -0.0001

Data Index: 782753 (C4 (Web Text))

Max Activating Token Index: 692