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

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

Neuron 1608 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4518. Min Range: -0.4518

Max Act: 0.4518. Min Act: -0.0000

Data Index: 194906 (C4 (Web Text))

Max Activating Token Index: 908

Text #1

Max Range: 0.4518. Min Range: -0.4518

Max Act: 0.4242. Min Act: -0.0000

Data Index: 752660 (C4 (Web Text))

Max Activating Token Index: 20

Text #2

Max Range: 0.4518. Min Range: -0.4518

Max Act: 0.4098. Min Act: -0.0000

Data Index: 87365 (C4 (Web Text))

Max Activating Token Index: 566

Text #3

Max Range: 0.4518. Min Range: -0.4518

Max Act: 0.4001. Min Act: -0.0000

Data Index: 515541 (C4 (Web Text))

Max Activating Token Index: 502

Text #4

Max Range: 0.4518. Min Range: -0.4518

Max Act: 0.3819. Min Act: -0.0000

Data Index: 1222680 (C4 (Web Text))

Max Activating Token Index: 120

Text #5

Max Range: 0.4518. Min Range: -0.4518

Max Act: 0.3707. Min Act: -0.0000

Data Index: 1326318 (C4 (Web Text))

Max Activating Token Index: 546

Text #6

Max Range: 0.4518. Min Range: -0.4518

Max Act: 0.3760. Min Act: -0.0000

Data Index: 363167 (C4 (Web Text))

Max Activating Token Index: 255

Text #7

Max Range: 0.4518. Min Range: -0.4518

Max Act: 0.3677. Min Act: -0.0000

Data Index: 1359556 (C4 (Web Text))

Max Activating Token Index: 585

Text #8

Max Range: 0.4518. Min Range: -0.4518

Max Act: 0.3675. Min Act: -0.0000

Data Index: 1315350 (C4 (Web Text))

Max Activating Token Index: 746

Text #9

Max Range: 0.4518. Min Range: -0.4518

Max Act: 0.3719. Min Act: 0.0000

Data Index: 1404249 (Python Code)

Max Activating Token Index: 816

Text #10

Max Range: 0.4518. Min Range: -0.4518

Max Act: 0.3762. Min Act: -0.0000

Data Index: 1047174 (C4 (Web Text))

Max Activating Token Index: 946

Text #11

Max Range: 0.4518. Min Range: -0.4518

Max Act: 0.3582. Min Act: -0.0000

Data Index: 1024567 (C4 (Web Text))

Max Activating Token Index: 65

Text #12

Max Range: 0.4518. Min Range: -0.4518

Max Act: 0.3540. Min Act: -0.0000

Data Index: 1236602 (C4 (Web Text))

Max Activating Token Index: 392

Text #13

Max Range: 0.4518. Min Range: -0.4518

Max Act: 0.3500. Min Act: -0.0000

Data Index: 1169409 (C4 (Web Text))

Max Activating Token Index: 900

Text #14

Max Range: 0.4518. Min Range: -0.4518

Max Act: 0.3394. Min Act: -0.0000

Data Index: 591157 (C4 (Web Text))

Max Activating Token Index: 457

Text #15

Max Range: 0.4518. Min Range: -0.4518

Max Act: 0.3523. Min Act: -0.0000

Data Index: 1556237 (Python Code)

Max Activating Token Index: 339

Text #16

Max Range: 0.4518. Min Range: -0.4518

Max Act: 0.3333. Min Act: -0.0000

Data Index: 1341812 (C4 (Web Text))

Max Activating Token Index: 50

Text #17

Max Range: 0.4518. Min Range: -0.4518

Max Act: 0.3183. Min Act: -0.0000

Data Index: 1093014 (C4 (Web Text))

Max Activating Token Index: 379

Text #18

Max Range: 0.4518. Min Range: -0.4518

Max Act: 0.3138. Min Act: -0.0000

Data Index: 1224747 (C4 (Web Text))

Max Activating Token Index: 639

Text #19

Max Range: 0.4518. Min Range: -0.4518

Max Act: 0.3002. Min Act: -0.0000

Data Index: 1221218 (C4 (Web Text))

Max Activating Token Index: 440