Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1912 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0353. Min Act: -0.0003

Data Index: 445496 (C4 (Web Text))

Max Activating Token Index: 330

Text #1

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0354. Min Act: -0.0003

Data Index: 438490 (C4 (Web Text))

Max Activating Token Index: 937

Text #2

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0346. Min Act: -0.0004

Data Index: 1327414 (C4 (Web Text))

Max Activating Token Index: 187

Text #3

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0321. Min Act: -0.0003

Data Index: 1260478 (C4 (Web Text))

Max Activating Token Index: 547

Text #4

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0325. Min Act: -0.0003

Data Index: 1265292 (C4 (Web Text))

Max Activating Token Index: 273

Text #5

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0305. Min Act: -0.0003

Data Index: 1294607 (C4 (Web Text))

Max Activating Token Index: 1008

Text #6

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0311. Min Act: -0.0003

Data Index: 1498222 (Python Code)

Max Activating Token Index: 394

Text #7

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0309. Min Act: -0.0003

Data Index: 1359575 (C4 (Web Text))

Max Activating Token Index: 93

Text #8

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0320. Min Act: -0.0001

Data Index: 662008 (C4 (Web Text))

Max Activating Token Index: 626

Text #9

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0298. Min Act: -0.0003

Data Index: 1162236 (C4 (Web Text))

Max Activating Token Index: 856

Text #10

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0299. Min Act: -0.0002

Data Index: 260371 (C4 (Web Text))

Max Activating Token Index: 360

Text #11

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0299. Min Act: -0.0003

Data Index: 1084763 (C4 (Web Text))

Max Activating Token Index: 97

Text #12

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0314. Min Act: -0.0004

Data Index: 631491 (C4 (Web Text))

Max Activating Token Index: 662

Text #13

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0318. Min Act: -0.0003

Data Index: 255066 (C4 (Web Text))

Max Activating Token Index: 185

Text #14

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0300. Min Act: -0.0003

Data Index: 37364 (C4 (Web Text))

Max Activating Token Index: 699

Text #15

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0299. Min Act: -0.0003

Data Index: 1097871 (C4 (Web Text))

Max Activating Token Index: 885

Text #16

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0300. Min Act: -0.0003

Data Index: 1081525 (C4 (Web Text))

Max Activating Token Index: 884

Text #17

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0293. Min Act: -0.0003

Data Index: 574234 (C4 (Web Text))

Max Activating Token Index: 335

Text #18

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0302. Min Act: -0.0003

Data Index: 208158 (C4 (Web Text))

Max Activating Token Index: 469

Text #19

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0290. Min Act: -0.0003

Data Index: 918395 (C4 (Web Text))

Max Activating Token Index: 908