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

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

Neuron 247 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: 0.0570. Min Range: -0.0570

Max Act: 0.0570. Min Act: -0.0002

Data Index: 976195 (C4 (Web Text))

Max Activating Token Index: 667

Text #1

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0414. Min Act: -0.0003

Data Index: 99614 (C4 (Web Text))

Max Activating Token Index: 526

Text #2

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0410. Min Act: -0.0003

Data Index: 571636 (C4 (Web Text))

Max Activating Token Index: 302

Text #3

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0417. Min Act: -0.0003

Data Index: 125740 (C4 (Web Text))

Max Activating Token Index: 226

Text #4

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0404. Min Act: -0.0003

Data Index: 1139066 (C4 (Web Text))

Max Activating Token Index: 247

Text #5

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0401. Min Act: -0.0003

Data Index: 1013873 (C4 (Web Text))

Max Activating Token Index: 470

Text #6

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0392. Min Act: -0.0003

Data Index: 1149347 (C4 (Web Text))

Max Activating Token Index: 153

Text #7

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0420. Min Act: -0.0003

Data Index: 1033353 (C4 (Web Text))

Max Activating Token Index: 809

Text #8

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0367. Min Act: -0.0002

Data Index: 67661 (C4 (Web Text))

Max Activating Token Index: 265

Text #9

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0403. Min Act: -0.0003

Data Index: 1057865 (C4 (Web Text))

Max Activating Token Index: 746

Text #10

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0386. Min Act: -0.0003

Data Index: 1106094 (C4 (Web Text))

Max Activating Token Index: 577

Text #11

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0373. Min Act: -0.0003

Data Index: 151247 (C4 (Web Text))

Max Activating Token Index: 264

Text #12

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0366. Min Act: -0.0002

Data Index: 355767 (C4 (Web Text))

Max Activating Token Index: 365

Text #13

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0369. Min Act: -0.0003

Data Index: 1273469 (C4 (Web Text))

Max Activating Token Index: 703

Text #14

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0368. Min Act: -0.0002

Data Index: 1187099 (C4 (Web Text))

Max Activating Token Index: 352

Text #15

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0376. Min Act: -0.0003

Data Index: 1335774 (C4 (Web Text))

Max Activating Token Index: 877

Text #16

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0357. Min Act: -0.0003

Data Index: 945140 (C4 (Web Text))

Max Activating Token Index: 3

Text #17

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0340. Min Act: -0.0003

Data Index: 829696 (C4 (Web Text))

Max Activating Token Index: 83

Text #18

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0365. Min Act: -0.0003

Data Index: 754686 (C4 (Web Text))

Max Activating Token Index: 756

Text #19

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0342. Min Act: -0.0003

Data Index: 229356 (C4 (Web Text))

Max Activating Token Index: 547