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

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

Neuron 3138 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0490. Min Act: -0.0002

Data Index: 825242 (C4 (Web Text))

Max Activating Token Index: 786

Text #1

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0371. Min Act: -0.0002

Data Index: 696461 (C4 (Web Text))

Max Activating Token Index: 145

Text #2

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0304. Min Act: -0.0002

Data Index: 962971 (C4 (Web Text))

Max Activating Token Index: 760

Text #3

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0322. Min Act: -0.0002

Data Index: 661679 (C4 (Web Text))

Max Activating Token Index: 381

Text #4

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0316. Min Act: -0.0002

Data Index: 479236 (C4 (Web Text))

Max Activating Token Index: 301

Text #5

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0299. Min Act: -0.0002

Data Index: 832823 (C4 (Web Text))

Max Activating Token Index: 706

Text #6

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0294. Min Act: -0.0002

Data Index: 1239827 (C4 (Web Text))

Max Activating Token Index: 840

Text #7

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0295. Min Act: -0.0002

Data Index: 801832 (C4 (Web Text))

Max Activating Token Index: 467

Text #8

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0288. Min Act: -0.0002

Data Index: 621297 (C4 (Web Text))

Max Activating Token Index: 725

Text #9

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0290. Min Act: -0.0002

Data Index: 742952 (C4 (Web Text))

Max Activating Token Index: 594

Text #10

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0291. Min Act: -0.0002

Data Index: 859266 (C4 (Web Text))

Max Activating Token Index: 697

Text #11

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0288. Min Act: -0.0002

Data Index: 317733 (C4 (Web Text))

Max Activating Token Index: 403

Text #12

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0284. Min Act: -0.0002

Data Index: 1165672 (C4 (Web Text))

Max Activating Token Index: 43

Text #13

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0275. Min Act: -0.0002

Data Index: 1017247 (C4 (Web Text))

Max Activating Token Index: 724

Text #14

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0272. Min Act: -0.0002

Data Index: 417510 (C4 (Web Text))

Max Activating Token Index: 980

Text #15

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0268. Min Act: -0.0002

Data Index: 819145 (C4 (Web Text))

Max Activating Token Index: 687

Text #16

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0262. Min Act: -0.0002

Data Index: 304006 (C4 (Web Text))

Max Activating Token Index: 206

Text #17

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0269. Min Act: -0.0002

Data Index: 815460 (C4 (Web Text))

Max Activating Token Index: 923

Text #18

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0260. Min Act: -0.0002

Data Index: 1009275 (C4 (Web Text))

Max Activating Token Index: 863

Text #19

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0260. Min Act: -0.0002

Data Index: 239974 (C4 (Web Text))

Max Activating Token Index: 806