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

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

Neuron 4403 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0350. Min Act: -0.0002

Data Index: 1641245 (Python Code)

Max Activating Token Index: 312

Text #1

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0381. Min Act: -0.0002

Data Index: 174646 (C4 (Web Text))

Max Activating Token Index: 334

Text #2

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0349. Min Act: -0.0002

Data Index: 1209312 (C4 (Web Text))

Max Activating Token Index: 62

Text #3

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0361. Min Act: -0.0002

Data Index: 332547 (C4 (Web Text))

Max Activating Token Index: 363

Text #4

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0331. Min Act: -0.0002

Data Index: 910536 (C4 (Web Text))

Max Activating Token Index: 394

Text #5

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0349. Min Act: -0.0002

Data Index: 333848 (C4 (Web Text))

Max Activating Token Index: 60

Text #6

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0326. Min Act: -0.0002

Data Index: 672918 (C4 (Web Text))

Max Activating Token Index: 36

Text #7

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0310. Min Act: -0.0002

Data Index: 433001 (C4 (Web Text))

Max Activating Token Index: 998

Text #8

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0332. Min Act: -0.0002

Data Index: 1277541 (C4 (Web Text))

Max Activating Token Index: 377

Text #9

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0336. Min Act: -0.0002

Data Index: 731373 (C4 (Web Text))

Max Activating Token Index: 931

Text #10

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0282. Min Act: -0.0002

Data Index: 601660 (C4 (Web Text))

Max Activating Token Index: 620

Text #11

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0311. Min Act: -0.0002

Data Index: 1595472 (Python Code)

Max Activating Token Index: 12

Text #12

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0315. Min Act: -0.0002

Data Index: 701195 (C4 (Web Text))

Max Activating Token Index: 182

Text #13

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0298. Min Act: -0.0002

Data Index: 63074 (C4 (Web Text))

Max Activating Token Index: 809

Text #14

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0299. Min Act: -0.0002

Data Index: 374931 (C4 (Web Text))

Max Activating Token Index: 873

Text #15

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0291. Min Act: -0.0002

Data Index: 1243385 (C4 (Web Text))

Max Activating Token Index: 369

Text #16

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0284. Min Act: -0.0002

Data Index: 356023 (C4 (Web Text))

Max Activating Token Index: 649

Text #17

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0316. Min Act: -0.0002

Data Index: 489181 (C4 (Web Text))

Max Activating Token Index: 717

Text #18

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0279. Min Act: -0.0002

Data Index: 1428159 (Python Code)

Max Activating Token Index: 533

Text #19

Max Range: 0.0381. Min Range: -0.0381

Max Act: 0.0288. Min Act: -0.0002

Data Index: 1020249 (C4 (Web Text))

Max Activating Token Index: 849