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

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

Neuron 1516 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: 0.0488. Min Range: -0.0488

Max Act: 0.0488. Min Act: -0.0003

Data Index: 1253994 (C4 (Web Text))

Max Activating Token Index: 6

Text #1

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0443. Min Act: -0.0003

Data Index: 825597 (C4 (Web Text))

Max Activating Token Index: 20

Text #2

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0375. Min Act: -0.0002

Data Index: 1566349 (Python Code)

Max Activating Token Index: 231

Text #3

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0379. Min Act: -0.0003

Data Index: 1548062 (Python Code)

Max Activating Token Index: 115

Text #4

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0359. Min Act: -0.0003

Data Index: 1610512 (Python Code)

Max Activating Token Index: 144

Text #5

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0361. Min Act: -0.0003

Data Index: 1644481 (Python Code)

Max Activating Token Index: 127

Text #6

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0355. Min Act: -0.0003

Data Index: 649320 (C4 (Web Text))

Max Activating Token Index: 782

Text #7

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0366. Min Act: -0.0003

Data Index: 305864 (C4 (Web Text))

Max Activating Token Index: 218

Text #8

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0342. Min Act: -0.0003

Data Index: 1303060 (C4 (Web Text))

Max Activating Token Index: 825

Text #9

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0349. Min Act: -0.0003

Data Index: 1039852 (C4 (Web Text))

Max Activating Token Index: 486

Text #10

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0319. Min Act: -0.0003

Data Index: 945123 (C4 (Web Text))

Max Activating Token Index: 140

Text #11

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0331. Min Act: -0.0003

Data Index: 1473330 (Python Code)

Max Activating Token Index: 132

Text #12

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0337. Min Act: -0.0003

Data Index: 1039349 (C4 (Web Text))

Max Activating Token Index: 297

Text #13

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0327. Min Act: -0.0003

Data Index: 729050 (C4 (Web Text))

Max Activating Token Index: 270

Text #14

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0325. Min Act: -0.0002

Data Index: 1314505 (C4 (Web Text))

Max Activating Token Index: 24

Text #15

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0320. Min Act: -0.0003

Data Index: 1100235 (C4 (Web Text))

Max Activating Token Index: 658

Text #16

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0317. Min Act: -0.0003

Data Index: 1429200 (Python Code)

Max Activating Token Index: 41

Text #17

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0317. Min Act: -0.0003

Data Index: 111874 (C4 (Web Text))

Max Activating Token Index: 61

Text #18

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0315. Min Act: -0.0002

Data Index: 1382948 (Python Code)

Max Activating Token Index: 394

Text #19

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0313. Min Act: -0.0002

Data Index: 1399724 (Python Code)

Max Activating Token Index: 345