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

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

Neuron 2429 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3906. Min Range: -0.3906

Max Act: 0.3681. Min Act: -0.0000

Data Index: 1176280 (C4 (Web Text))

Max Activating Token Index: 90

Text #1

Max Range: 0.3906. Min Range: -0.3906

Max Act: 0.3554. Min Act: -0.0000

Data Index: 948169 (C4 (Web Text))

Max Activating Token Index: 474

Text #2

Max Range: 0.3906. Min Range: -0.3906

Max Act: 0.3906. Min Act: -0.0000

Data Index: 1320645 (C4 (Web Text))

Max Activating Token Index: 667

Text #3

Max Range: 0.3906. Min Range: -0.3906

Max Act: 0.3512. Min Act: -0.0001

Data Index: 1238496 (C4 (Web Text))

Max Activating Token Index: 744

Text #4

Max Range: 0.3906. Min Range: -0.3906

Max Act: 0.3457. Min Act: -0.0000

Data Index: 1266139 (C4 (Web Text))

Max Activating Token Index: 362

Text #5

Max Range: 0.3906. Min Range: -0.3906

Max Act: 0.3584. Min Act: -0.0000

Data Index: 178842 (C4 (Web Text))

Max Activating Token Index: 541

Text #6

Max Range: 0.3906. Min Range: -0.3906

Max Act: 0.3457. Min Act: -0.0000

Data Index: 543870 (C4 (Web Text))

Max Activating Token Index: 514

Text #7

Max Range: 0.3906. Min Range: -0.3906

Max Act: 0.3428. Min Act: -0.0001

Data Index: 53444 (C4 (Web Text))

Max Activating Token Index: 196

Text #8

Max Range: 0.3906. Min Range: -0.3906

Max Act: 0.3333. Min Act: -0.0000

Data Index: 565498 (C4 (Web Text))

Max Activating Token Index: 389

Text #9

Max Range: 0.3906. Min Range: -0.3906

Max Act: 0.3216. Min Act: -0.0001

Data Index: 1199457 (C4 (Web Text))

Max Activating Token Index: 294

Text #10

Max Range: 0.3906. Min Range: -0.3906

Max Act: 0.3501. Min Act: -0.0001

Data Index: 870934 (C4 (Web Text))

Max Activating Token Index: 327

Text #11

Max Range: 0.3906. Min Range: -0.3906

Max Act: 0.3278. Min Act: -0.0001

Data Index: 550782 (C4 (Web Text))

Max Activating Token Index: 298

Text #12

Max Range: 0.3906. Min Range: -0.3906

Max Act: 0.3288. Min Act: -0.0000

Data Index: 707450 (C4 (Web Text))

Max Activating Token Index: 374

Text #13

Max Range: 0.3906. Min Range: -0.3906

Max Act: 0.3329. Min Act: -0.0001

Data Index: 1048381 (C4 (Web Text))

Max Activating Token Index: 139

Text #14

Max Range: 0.3906. Min Range: -0.3906

Max Act: 0.3428. Min Act: -0.0001

Data Index: 308299 (C4 (Web Text))

Max Activating Token Index: 196

Text #15

Max Range: 0.3906. Min Range: -0.3906

Max Act: 0.3065. Min Act: -0.0000

Data Index: 873819 (C4 (Web Text))

Max Activating Token Index: 63

Text #16

Max Range: 0.3906. Min Range: -0.3906

Max Act: 0.3131. Min Act: -0.0001

Data Index: 800380 (C4 (Web Text))

Max Activating Token Index: 549

Text #17

Max Range: 0.3906. Min Range: -0.3906

Max Act: 0.3035. Min Act: -0.0001

Data Index: 340505 (C4 (Web Text))

Max Activating Token Index: 949

Text #18

Max Range: 0.3906. Min Range: -0.3906

Max Act: 0.3108. Min Act: -0.0001

Data Index: 529346 (C4 (Web Text))

Max Activating Token Index: 180

Text #19

Max Range: 0.3906. Min Range: -0.3906

Max Act: 0.2899. Min Act: -0.0000

Data Index: 802569 (C4 (Web Text))

Max Activating Token Index: 908