Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 988 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.3392. Min Act: -0.0005

Data Index: 1218092 (C4 (Web Text))

Max Activating Token Index: 898

Text #1

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.3487. Min Act: -0.0005

Data Index: 272888 (C4 (Web Text))

Max Activating Token Index: 870

Text #2

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.3575. Min Act: -0.0005

Data Index: 1247351 (C4 (Web Text))

Max Activating Token Index: 433

Text #3

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.3433. Min Act: -0.0005

Data Index: 1235169 (C4 (Web Text))

Max Activating Token Index: 690

Text #4

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.3527. Min Act: -0.0005

Data Index: 179408 (C4 (Web Text))

Max Activating Token Index: 892

Text #5

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.3396. Min Act: -0.0005

Data Index: 843326 (C4 (Web Text))

Max Activating Token Index: 604

Text #6

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.3270. Min Act: -0.0005

Data Index: 1326071 (C4 (Web Text))

Max Activating Token Index: 635

Text #7

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.3372. Min Act: -0.0005

Data Index: 941687 (C4 (Web Text))

Max Activating Token Index: 807

Text #8

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.3426. Min Act: -0.0005

Data Index: 673185 (C4 (Web Text))

Max Activating Token Index: 643

Text #9

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.3082. Min Act: -0.0005

Data Index: 717818 (C4 (Web Text))

Max Activating Token Index: 446

Text #10

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.3246. Min Act: -0.0005

Data Index: 1147306 (C4 (Web Text))

Max Activating Token Index: 656

Text #11

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.3326. Min Act: -0.0005

Data Index: 447199 (C4 (Web Text))

Max Activating Token Index: 299

Text #12

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.3278. Min Act: -0.0005

Data Index: 998324 (C4 (Web Text))

Max Activating Token Index: 650

Text #13

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.3042. Min Act: -0.0005

Data Index: 93407 (C4 (Web Text))

Max Activating Token Index: 872

Text #14

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.3191. Min Act: -0.0005

Data Index: 693313 (C4 (Web Text))

Max Activating Token Index: 591

Text #15

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.3178. Min Act: -0.0005

Data Index: 630839 (C4 (Web Text))

Max Activating Token Index: 794

Text #16

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.3310. Min Act: -0.0005

Data Index: 2828 (C4 (Web Text))

Max Activating Token Index: 365

Text #17

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.3076. Min Act: -0.0005

Data Index: 422246 (C4 (Web Text))

Max Activating Token Index: 730

Text #18

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.3174. Min Act: -0.0005

Data Index: 235183 (C4 (Web Text))

Max Activating Token Index: 757

Text #19

Max Range: 0.3575. Min Range: -0.3575

Max Act: 0.2910. Min Act: -0.0005

Data Index: 909964 (C4 (Web Text))

Max Activating Token Index: 845