Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1602 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.2917. Min Act: -0.0003

Data Index: 1430273 (Python Code)

Max Activating Token Index: 575

Text #1

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.2700. Min Act: -0.0003

Data Index: 749649 (C4 (Web Text))

Max Activating Token Index: 235

Text #2

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.2544. Min Act: -0.0003

Data Index: 1293384 (C4 (Web Text))

Max Activating Token Index: 814

Text #3

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.2758. Min Act: -0.0003

Data Index: 182321 (C4 (Web Text))

Max Activating Token Index: 694

Text #4

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.2550. Min Act: -0.0003

Data Index: 1480279 (Python Code)

Max Activating Token Index: 36

Text #5

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.2590. Min Act: -0.0003

Data Index: 341746 (C4 (Web Text))

Max Activating Token Index: 325

Text #6

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.2580. Min Act: -0.0003

Data Index: 85540 (C4 (Web Text))

Max Activating Token Index: 584

Text #7

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.2550. Min Act: -0.0002

Data Index: 1593503 (Python Code)

Max Activating Token Index: 614

Text #8

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.2507. Min Act: -0.0003

Data Index: 1280009 (C4 (Web Text))

Max Activating Token Index: 734

Text #9

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.2440. Min Act: -0.0003

Data Index: 429530 (C4 (Web Text))

Max Activating Token Index: 993

Text #10

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.2404. Min Act: -0.0003

Data Index: 97389 (C4 (Web Text))

Max Activating Token Index: 658

Text #11

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.2302. Min Act: -0.0003

Data Index: 1386773 (Python Code)

Max Activating Token Index: 72

Text #12

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.2320. Min Act: -0.0003

Data Index: 1353557 (C4 (Web Text))

Max Activating Token Index: 223

Text #13

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.2299. Min Act: -0.0003

Data Index: 617089 (C4 (Web Text))

Max Activating Token Index: 479

Text #14

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.2313. Min Act: -0.0003

Data Index: 427586 (C4 (Web Text))

Max Activating Token Index: 342

Text #15

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.2174. Min Act: -0.0003

Data Index: 1243096 (C4 (Web Text))

Max Activating Token Index: 462

Text #16

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.2267. Min Act: -0.0003

Data Index: 849978 (C4 (Web Text))

Max Activating Token Index: 109

Text #17

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.2252. Min Act: -0.0003

Data Index: 162206 (C4 (Web Text))

Max Activating Token Index: 317

Text #18

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.2090. Min Act: -0.0003

Data Index: 1000112 (C4 (Web Text))

Max Activating Token Index: 211

Text #19

Max Range: 0.2917. Min Range: -0.2917

Max Act: 0.2242. Min Act: -0.0003

Data Index: 110474 (C4 (Web Text))

Max Activating Token Index: 582