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

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

Neuron 3264 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0574. Min Act: -0.0000

Data Index: 8563 (C4 (Web Text))

Max Activating Token Index: 291

Text #1

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0422. Min Act: -0.0000

Data Index: 764610 (C4 (Web Text))

Max Activating Token Index: 343

Text #2

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0400. Min Act: -0.0000

Data Index: 72954 (C4 (Web Text))

Max Activating Token Index: 677

Text #3

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0354. Min Act: -0.0000

Data Index: 78467 (C4 (Web Text))

Max Activating Token Index: 51

Text #4

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0322. Min Act: -0.0000

Data Index: 383609 (C4 (Web Text))

Max Activating Token Index: 163

Text #5

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0325. Min Act: -0.0000

Data Index: 87390 (C4 (Web Text))

Max Activating Token Index: 138

Text #6

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0337. Min Act: -0.0000

Data Index: 1242446 (C4 (Web Text))

Max Activating Token Index: 425

Text #7

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0359. Min Act: -0.0000

Data Index: 714776 (C4 (Web Text))

Max Activating Token Index: 576

Text #8

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0333. Min Act: -0.0000

Data Index: 1321436 (C4 (Web Text))

Max Activating Token Index: 77

Text #9

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0346. Min Act: -0.0000

Data Index: 1359806 (C4 (Web Text))

Max Activating Token Index: 930

Text #10

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0315. Min Act: -0.0000

Data Index: 139202 (C4 (Web Text))

Max Activating Token Index: 522

Text #11

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0337. Min Act: -0.0000

Data Index: 1431848 (Python Code)

Max Activating Token Index: 36

Text #12

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0313. Min Act: -0.0000

Data Index: 1031667 (C4 (Web Text))

Max Activating Token Index: 911

Text #13

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0311. Min Act: -0.0000

Data Index: 1003603 (C4 (Web Text))

Max Activating Token Index: 133

Text #14

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0306. Min Act: -0.0000

Data Index: 1408517 (Python Code)

Max Activating Token Index: 874

Text #15

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0311. Min Act: -0.0000

Data Index: 421766 (C4 (Web Text))

Max Activating Token Index: 592

Text #16

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0324. Min Act: -0.0000

Data Index: 947430 (C4 (Web Text))

Max Activating Token Index: 637

Text #17

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0299. Min Act: -0.0000

Data Index: 338876 (C4 (Web Text))

Max Activating Token Index: 805

Text #18

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0310. Min Act: -0.0000

Data Index: 130883 (C4 (Web Text))

Max Activating Token Index: 442

Text #19

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0313. Min Act: -0.0000

Data Index: 691283 (C4 (Web Text))

Max Activating Token Index: 770