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

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

Neuron 1880 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.3340. Min Act: -0.0000

Data Index: 38491 (C4 (Web Text))

Max Activating Token Index: 321

Text #1

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.3193. Min Act: -0.0000

Data Index: 495639 (C4 (Web Text))

Max Activating Token Index: 430

Text #2

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2883. Min Act: -0.0000

Data Index: 382068 (C4 (Web Text))

Max Activating Token Index: 396

Text #3

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2773. Min Act: -0.0000

Data Index: 195703 (C4 (Web Text))

Max Activating Token Index: 675

Text #4

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2580. Min Act: -0.0000

Data Index: 359425 (C4 (Web Text))

Max Activating Token Index: 130

Text #5

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2472. Min Act: -0.0001

Data Index: 1140178 (C4 (Web Text))

Max Activating Token Index: 61

Text #6

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2359. Min Act: -0.0000

Data Index: 81767 (C4 (Web Text))

Max Activating Token Index: 109

Text #7

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2495. Min Act: -0.0000

Data Index: 354972 (C4 (Web Text))

Max Activating Token Index: 946

Text #8

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2349. Min Act: -0.0000

Data Index: 949248 (C4 (Web Text))

Max Activating Token Index: 923

Text #9

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2441. Min Act: -0.0001

Data Index: 806893 (C4 (Web Text))

Max Activating Token Index: 609

Text #10

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2411. Min Act: -0.0000

Data Index: 891063 (C4 (Web Text))

Max Activating Token Index: 795

Text #11

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2411. Min Act: -0.0000

Data Index: 780379 (C4 (Web Text))

Max Activating Token Index: 463

Text #12

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2488. Min Act: -0.0000

Data Index: 80758 (C4 (Web Text))

Max Activating Token Index: 948

Text #13

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2342. Min Act: -0.0000

Data Index: 446158 (C4 (Web Text))

Max Activating Token Index: 515

Text #14

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2288. Min Act: -0.0001

Data Index: 182908 (C4 (Web Text))

Max Activating Token Index: 520

Text #15

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2202. Min Act: -0.0001

Data Index: 366616 (C4 (Web Text))

Max Activating Token Index: 73

Text #16

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2324. Min Act: -0.0000

Data Index: 205441 (C4 (Web Text))

Max Activating Token Index: 390

Text #17

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2170. Min Act: -0.0001

Data Index: 124272 (C4 (Web Text))

Max Activating Token Index: 567

Text #18

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2312. Min Act: -0.0001

Data Index: 140745 (C4 (Web Text))

Max Activating Token Index: 614

Text #19

Max Range: 0.3340. Min Range: -0.3340

Max Act: 0.2258. Min Act: -0.0000

Data Index: 92237 (C4 (Web Text))

Max Activating Token Index: 521