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

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

Neuron 2189 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0438. Min Act: -0.0001

Data Index: 717790 (C4 (Web Text))

Max Activating Token Index: 975

Text #1

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0452. Min Act: -0.0001

Data Index: 1563349 (Python Code)

Max Activating Token Index: 609

Text #2

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0451. Min Act: -0.0001

Data Index: 1313432 (C4 (Web Text))

Max Activating Token Index: 417

Text #3

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0359. Min Act: -0.0000

Data Index: 479079 (C4 (Web Text))

Max Activating Token Index: 212

Text #4

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0317. Min Act: -0.0001

Data Index: 616509 (C4 (Web Text))

Max Activating Token Index: 375

Text #5

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0325. Min Act: -0.0000

Data Index: 86317 (C4 (Web Text))

Max Activating Token Index: 328

Text #6

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0327. Min Act: -0.0001

Data Index: 682824 (C4 (Web Text))

Max Activating Token Index: 59

Text #7

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0317. Min Act: -0.0001

Data Index: 606226 (C4 (Web Text))

Max Activating Token Index: 796

Text #8

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0317. Min Act: -0.0001

Data Index: 157197 (C4 (Web Text))

Max Activating Token Index: 68

Text #9

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0296. Min Act: -0.0001

Data Index: 1613360 (Python Code)

Max Activating Token Index: 288

Text #10

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0313. Min Act: -0.0000

Data Index: 584208 (C4 (Web Text))

Max Activating Token Index: 503

Text #11

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0304. Min Act: -0.0001

Data Index: 1023918 (C4 (Web Text))

Max Activating Token Index: 365

Text #12

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0310. Min Act: -0.0001

Data Index: 1505471 (Python Code)

Max Activating Token Index: 556

Text #13

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0348. Min Act: -0.0001

Data Index: 1550533 (Python Code)

Max Activating Token Index: 1001

Text #14

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0283. Min Act: -0.0000

Data Index: 1173622 (C4 (Web Text))

Max Activating Token Index: 787

Text #15

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0301. Min Act: -0.0001

Data Index: 1529540 (Python Code)

Max Activating Token Index: 654

Text #16

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0288. Min Act: -0.0001

Data Index: 814355 (C4 (Web Text))

Max Activating Token Index: 76

Text #17

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0317. Min Act: -0.0000

Data Index: 998117 (C4 (Web Text))

Max Activating Token Index: 502

Text #18

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0263. Min Act: -0.0001

Data Index: 1523546 (Python Code)

Max Activating Token Index: 703

Text #19

Max Range: 0.0452. Min Range: -0.0452

Max Act: 0.0314. Min Act: -0.0000

Data Index: 1233802 (C4 (Web Text))

Max Activating Token Index: 588