Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3858 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0314. Min Act: -0.0003

Data Index: 647387 (C4 (Web Text))

Max Activating Token Index: 922

Text #1

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0405. Min Act: -0.0003

Data Index: 821140 (C4 (Web Text))

Max Activating Token Index: 389

Text #2

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0413. Min Act: -0.0003

Data Index: 430838 (C4 (Web Text))

Max Activating Token Index: 55

Text #3

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0319. Min Act: -0.0003

Data Index: 1213654 (C4 (Web Text))

Max Activating Token Index: 873

Text #4

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0388. Min Act: -0.0003

Data Index: 1263099 (C4 (Web Text))

Max Activating Token Index: 281

Text #5

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0367. Min Act: -0.0003

Data Index: 1346138 (C4 (Web Text))

Max Activating Token Index: 14

Text #6

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0345. Min Act: -0.0003

Data Index: 269847 (C4 (Web Text))

Max Activating Token Index: 21

Text #7

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0324. Min Act: -0.0003

Data Index: 1545951 (Python Code)

Max Activating Token Index: 589

Text #8

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0269. Min Act: -0.0003

Data Index: 532785 (C4 (Web Text))

Max Activating Token Index: 618

Text #9

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0372. Min Act: -0.0003

Data Index: 4070 (C4 (Web Text))

Max Activating Token Index: 995

Text #10

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0323. Min Act: -0.0003

Data Index: 1489339 (Python Code)

Max Activating Token Index: 732

Text #11

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0363. Min Act: -0.0003

Data Index: 380307 (C4 (Web Text))

Max Activating Token Index: 967

Text #12

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0353. Min Act: -0.0003

Data Index: 1169444 (C4 (Web Text))

Max Activating Token Index: 402

Text #13

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0319. Min Act: -0.0003

Data Index: 270724 (C4 (Web Text))

Max Activating Token Index: 187

Text #14

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0343. Min Act: -0.0003

Data Index: 1580982 (Python Code)

Max Activating Token Index: 735

Text #15

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0316. Min Act: -0.0003

Data Index: 680064 (C4 (Web Text))

Max Activating Token Index: 593

Text #16

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0332. Min Act: -0.0003

Data Index: 1556023 (Python Code)

Max Activating Token Index: 85

Text #17

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0309. Min Act: -0.0003

Data Index: 1005832 (C4 (Web Text))

Max Activating Token Index: 79

Text #18

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0337. Min Act: -0.0003

Data Index: 451341 (C4 (Web Text))

Max Activating Token Index: 19

Text #19

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0313. Min Act: -0.0003

Data Index: 286896 (C4 (Web Text))

Max Activating Token Index: 225