Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1122 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0409. Min Act: -0.0003

Data Index: 574376 (C4 (Web Text))

Max Activating Token Index: 606

Text #1

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0352. Min Act: -0.0003

Data Index: 440350 (C4 (Web Text))

Max Activating Token Index: 791

Text #2

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0353. Min Act: -0.0003

Data Index: 526274 (C4 (Web Text))

Max Activating Token Index: 238

Text #3

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0341. Min Act: -0.0003

Data Index: 1569226 (Python Code)

Max Activating Token Index: 524

Text #4

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0331. Min Act: -0.0003

Data Index: 98294 (C4 (Web Text))

Max Activating Token Index: 751

Text #5

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0334. Min Act: -0.0003

Data Index: 1261536 (C4 (Web Text))

Max Activating Token Index: 133

Text #6

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0329. Min Act: -0.0003

Data Index: 1185491 (C4 (Web Text))

Max Activating Token Index: 265

Text #7

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0320. Min Act: -0.0003

Data Index: 1361132 (Python Code)

Max Activating Token Index: 1002

Text #8

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0320. Min Act: -0.0003

Data Index: 88902 (C4 (Web Text))

Max Activating Token Index: 27

Text #9

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0319. Min Act: -0.0003

Data Index: 91917 (C4 (Web Text))

Max Activating Token Index: 365

Text #10

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0299. Min Act: -0.0003

Data Index: 1643647 (Python Code)

Max Activating Token Index: 331

Text #11

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0311. Min Act: -0.0003

Data Index: 907495 (C4 (Web Text))

Max Activating Token Index: 533

Text #12

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0309. Min Act: -0.0003

Data Index: 572417 (C4 (Web Text))

Max Activating Token Index: 667

Text #13

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0305. Min Act: -0.0004

Data Index: 254628 (C4 (Web Text))

Max Activating Token Index: 182

Text #14

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0298. Min Act: -0.0003

Data Index: 1531237 (Python Code)

Max Activating Token Index: 236

Text #15

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0300. Min Act: -0.0003

Data Index: 854802 (C4 (Web Text))

Max Activating Token Index: 537

Text #16

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0300. Min Act: -0.0004

Data Index: 1216545 (C4 (Web Text))

Max Activating Token Index: 376

Text #17

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0296. Min Act: -0.0003

Data Index: 1219909 (C4 (Web Text))

Max Activating Token Index: 757

Text #18

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0301. Min Act: -0.0003

Data Index: 489874 (C4 (Web Text))

Max Activating Token Index: 138

Text #19

Max Range: 0.0409. Min Range: -0.0409

Max Act: 0.0300. Min Act: -0.0002

Data Index: 989308 (C4 (Web Text))

Max Activating Token Index: 172