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

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

Neuron 2207 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: 4.9331. Min Range: -4.9331

Max Act: 4.9331. Min Act: -0.0000

Data Index: 733706 (C4 (Web Text))

Max Activating Token Index: 225

Text #1

Max Range: 4.9331. Min Range: -4.9331

Max Act: 3.9865. Min Act: -0.0000

Data Index: 895142 (C4 (Web Text))

Max Activating Token Index: 7

Text #2

Max Range: 4.9331. Min Range: -4.9331

Max Act: 3.8411. Min Act: -0.0000

Data Index: 499824 (C4 (Web Text))

Max Activating Token Index: 572

Text #3

Max Range: 4.9331. Min Range: -4.9331

Max Act: 4.0361. Min Act: -0.0000

Data Index: 551496 (C4 (Web Text))

Max Activating Token Index: 347

Text #4

Max Range: 4.9331. Min Range: -4.9331

Max Act: 3.6353. Min Act: -0.0000

Data Index: 476046 (C4 (Web Text))

Max Activating Token Index: 940

Text #5

Max Range: 4.9331. Min Range: -4.9331

Max Act: 3.3281. Min Act: -0.0000

Data Index: 727139 (C4 (Web Text))

Max Activating Token Index: 489

Text #6

Max Range: 4.9331. Min Range: -4.9331

Max Act: 3.1928. Min Act: -0.0000

Data Index: 357701 (C4 (Web Text))

Max Activating Token Index: 432

Text #7

Max Range: 4.9331. Min Range: -4.9331

Max Act: 3.3104. Min Act: -0.0000

Data Index: 56144 (C4 (Web Text))

Max Activating Token Index: 265

Text #8

Max Range: 4.9331. Min Range: -4.9331

Max Act: 3.2902. Min Act: -0.0000

Data Index: 80160 (C4 (Web Text))

Max Activating Token Index: 822

Text #9

Max Range: 4.9331. Min Range: -4.9331

Max Act: 3.2540. Min Act: -0.0000

Data Index: 1228134 (C4 (Web Text))

Max Activating Token Index: 9

Text #10

Max Range: 4.9331. Min Range: -4.9331

Max Act: 3.2370. Min Act: -0.0000

Data Index: 1310167 (C4 (Web Text))

Max Activating Token Index: 692

Text #11

Max Range: 4.9331. Min Range: -4.9331

Max Act: 3.1252. Min Act: -0.0000

Data Index: 274971 (C4 (Web Text))

Max Activating Token Index: 250

Text #12

Max Range: 4.9331. Min Range: -4.9331

Max Act: 3.2475. Min Act: -0.0000

Data Index: 741714 (C4 (Web Text))

Max Activating Token Index: 136

Text #13

Max Range: 4.9331. Min Range: -4.9331

Max Act: 3.2568. Min Act: -0.0000

Data Index: 1079509 (C4 (Web Text))

Max Activating Token Index: 408

Text #14

Max Range: 4.9331. Min Range: -4.9331

Max Act: 3.1835. Min Act: -0.0000

Data Index: 760550 (C4 (Web Text))

Max Activating Token Index: 116

Text #15

Max Range: 4.9331. Min Range: -4.9331

Max Act: 3.3435. Min Act: -0.0000

Data Index: 728318 (C4 (Web Text))

Max Activating Token Index: 560

Text #16

Max Range: 4.9331. Min Range: -4.9331

Max Act: 3.0606. Min Act: -0.0000

Data Index: 1088356 (C4 (Web Text))

Max Activating Token Index: 492

Text #17

Max Range: 4.9331. Min Range: -4.9331

Max Act: 3.3314. Min Act: -0.0000

Data Index: 340307 (C4 (Web Text))

Max Activating Token Index: 850

Text #18

Max Range: 4.9331. Min Range: -4.9331

Max Act: 3.0396. Min Act: -0.0000

Data Index: 1304466 (C4 (Web Text))

Max Activating Token Index: 389

Text #19

Max Range: 4.9331. Min Range: -4.9331

Max Act: 3.1882. Min Act: -0.0000

Data Index: 322555 (C4 (Web Text))

Max Activating Token Index: 325