Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3876 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4226. Min Range: -0.4226

Max Act: 0.4149. Min Act: -0.0000

Data Index: 1259998 (C4 (Web Text))

Max Activating Token Index: 607

Text #1

Max Range: 0.4226. Min Range: -0.4226

Max Act: 0.4226. Min Act: -0.0000

Data Index: 348087 (C4 (Web Text))

Max Activating Token Index: 810

Text #2

Max Range: 0.4226. Min Range: -0.4226

Max Act: 0.3824. Min Act: -0.0000

Data Index: 699494 (C4 (Web Text))

Max Activating Token Index: 777

Text #3

Max Range: 0.4226. Min Range: -0.4226

Max Act: 0.3878. Min Act: -0.0000

Data Index: 558606 (C4 (Web Text))

Max Activating Token Index: 623

Text #4

Max Range: 0.4226. Min Range: -0.4226

Max Act: 0.3688. Min Act: -0.0000

Data Index: 107225 (C4 (Web Text))

Max Activating Token Index: 22

Text #5

Max Range: 0.4226. Min Range: -0.4226

Max Act: 0.3642. Min Act: -0.0000

Data Index: 567401 (C4 (Web Text))

Max Activating Token Index: 344

Text #6

Max Range: 0.4226. Min Range: -0.4226

Max Act: 0.3628. Min Act: -0.0000

Data Index: 1126444 (C4 (Web Text))

Max Activating Token Index: 27

Text #7

Max Range: 0.4226. Min Range: -0.4226

Max Act: 0.3605. Min Act: -0.0000

Data Index: 296355 (C4 (Web Text))

Max Activating Token Index: 712

Text #8

Max Range: 0.4226. Min Range: -0.4226

Max Act: 0.3443. Min Act: -0.0000

Data Index: 534114 (C4 (Web Text))

Max Activating Token Index: 331

Text #9

Max Range: 0.4226. Min Range: -0.4226

Max Act: 0.3852. Min Act: -0.0000

Data Index: 202108 (C4 (Web Text))

Max Activating Token Index: 144

Text #10

Max Range: 0.4226. Min Range: -0.4226

Max Act: 0.3646. Min Act: -0.0000

Data Index: 346660 (C4 (Web Text))

Max Activating Token Index: 112

Text #11

Max Range: 0.4226. Min Range: -0.4226

Max Act: 0.3451. Min Act: -0.0000

Data Index: 452399 (C4 (Web Text))

Max Activating Token Index: 953

Text #12

Max Range: 0.4226. Min Range: -0.4226

Max Act: 0.3464. Min Act: -0.0000

Data Index: 130825 (C4 (Web Text))

Max Activating Token Index: 81

Text #13

Max Range: 0.4226. Min Range: -0.4226

Max Act: 0.3555. Min Act: -0.0000

Data Index: 575681 (C4 (Web Text))

Max Activating Token Index: 282

Text #14

Max Range: 0.4226. Min Range: -0.4226

Max Act: 0.3491. Min Act: -0.0000

Data Index: 690755 (C4 (Web Text))

Max Activating Token Index: 434

Text #15

Max Range: 0.4226. Min Range: -0.4226

Max Act: 0.3486. Min Act: -0.0000

Data Index: 1001009 (C4 (Web Text))

Max Activating Token Index: 310

Text #16

Max Range: 0.4226. Min Range: -0.4226

Max Act: 0.3106. Min Act: -0.0000

Data Index: 1185777 (C4 (Web Text))

Max Activating Token Index: 837

Text #17

Max Range: 0.4226. Min Range: -0.4226

Max Act: 0.3363. Min Act: -0.0000

Data Index: 353476 (C4 (Web Text))

Max Activating Token Index: 242

Text #18

Max Range: 0.4226. Min Range: -0.4226

Max Act: 0.2958. Min Act: -0.0000

Data Index: 958644 (C4 (Web Text))

Max Activating Token Index: 301

Text #19

Max Range: 0.4226. Min Range: -0.4226

Max Act: 0.3178. Min Act: -0.0000

Data Index: 1282934 (C4 (Web Text))

Max Activating Token Index: 1008