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

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

Neuron 3449 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6937. Min Range: -3.6937

Max Act: 3.6937. Min Act: -0.0000

Data Index: 265203 (C4 (Web Text))

Max Activating Token Index: 170

Text #1

Max Range: 3.6937. Min Range: -3.6937

Max Act: 3.3927. Min Act: -0.0000

Data Index: 666920 (C4 (Web Text))

Max Activating Token Index: 716

Text #2

Max Range: 3.6937. Min Range: -3.6937

Max Act: 3.5214. Min Act: -0.0000

Data Index: 824632 (C4 (Web Text))

Max Activating Token Index: 436

Text #3

Max Range: 3.6937. Min Range: -3.6937

Max Act: 3.3198. Min Act: -0.0000

Data Index: 1135440 (C4 (Web Text))

Max Activating Token Index: 704

Text #4

Max Range: 3.6937. Min Range: -3.6937

Max Act: 3.2169. Min Act: -0.0000

Data Index: 753025 (C4 (Web Text))

Max Activating Token Index: 231

Text #5

Max Range: 3.6937. Min Range: -3.6937

Max Act: 3.1387. Min Act: -0.0000

Data Index: 583431 (C4 (Web Text))

Max Activating Token Index: 21

Text #6

Max Range: 3.6937. Min Range: -3.6937

Max Act: 3.1020. Min Act: -0.0000

Data Index: 711221 (C4 (Web Text))

Max Activating Token Index: 973

Text #7

Max Range: 3.6937. Min Range: -3.6937

Max Act: 3.0572. Min Act: -0.0000

Data Index: 508027 (C4 (Web Text))

Max Activating Token Index: 958

Text #8

Max Range: 3.6937. Min Range: -3.6937

Max Act: 2.4997. Min Act: -0.0000

Data Index: 312700 (C4 (Web Text))

Max Activating Token Index: 878

Text #9

Max Range: 3.6937. Min Range: -3.6937

Max Act: 2.8774. Min Act: -0.0000

Data Index: 536075 (C4 (Web Text))

Max Activating Token Index: 292

Text #10

Max Range: 3.6937. Min Range: -3.6937

Max Act: 2.8038. Min Act: -0.0000

Data Index: 1192817 (C4 (Web Text))

Max Activating Token Index: 748

Text #11

Max Range: 3.6937. Min Range: -3.6937

Max Act: 2.6806. Min Act: -0.0000

Data Index: 189995 (C4 (Web Text))

Max Activating Token Index: 205

Text #12

Max Range: 3.6937. Min Range: -3.6937

Max Act: 3.0100. Min Act: -0.0000

Data Index: 529065 (C4 (Web Text))

Max Activating Token Index: 165

Text #13

Max Range: 3.6937. Min Range: -3.6937

Max Act: 2.6098. Min Act: -0.0000

Data Index: 670839 (C4 (Web Text))

Max Activating Token Index: 339

Text #14

Max Range: 3.6937. Min Range: -3.6937

Max Act: 2.8626. Min Act: -0.0000

Data Index: 1344231 (C4 (Web Text))

Max Activating Token Index: 560

Text #15

Max Range: 3.6937. Min Range: -3.6937

Max Act: 2.8482. Min Act: -0.0000

Data Index: 149196 (C4 (Web Text))

Max Activating Token Index: 626

Text #16

Max Range: 3.6937. Min Range: -3.6937

Max Act: 2.8315. Min Act: -0.0000

Data Index: 851431 (C4 (Web Text))

Max Activating Token Index: 584

Text #17

Max Range: 3.6937. Min Range: -3.6937

Max Act: 2.9644. Min Act: -0.0000

Data Index: 15388 (C4 (Web Text))

Max Activating Token Index: 58

Text #18

Max Range: 3.6937. Min Range: -3.6937

Max Act: 2.7564. Min Act: -0.0000

Data Index: 1284028 (C4 (Web Text))

Max Activating Token Index: 363

Text #19

Max Range: 3.6937. Min Range: -3.6937

Max Act: 2.7609. Min Act: -0.0000

Data Index: 706604 (C4 (Web Text))

Max Activating Token Index: 249