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

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

Neuron 3991 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2756. Min Range: -0.2756

Max Act: 0.2756. Min Act: -0.0002

Data Index: 431649 (C4 (Web Text))

Max Activating Token Index: 315

Text #1

Max Range: 0.2756. Min Range: -0.2756

Max Act: 0.2667. Min Act: -0.0003

Data Index: 47220 (C4 (Web Text))

Max Activating Token Index: 766

Text #2

Max Range: 0.2756. Min Range: -0.2756

Max Act: 0.2555. Min Act: -0.0003

Data Index: 683132 (C4 (Web Text))

Max Activating Token Index: 121

Text #3

Max Range: 0.2756. Min Range: -0.2756

Max Act: 0.2512. Min Act: -0.0002

Data Index: 1354404 (C4 (Web Text))

Max Activating Token Index: 64

Text #4

Max Range: 0.2756. Min Range: -0.2756

Max Act: 0.2476. Min Act: -0.0003

Data Index: 381762 (C4 (Web Text))

Max Activating Token Index: 870

Text #5

Max Range: 0.2756. Min Range: -0.2756

Max Act: 0.2465. Min Act: -0.0003

Data Index: 1323038 (C4 (Web Text))

Max Activating Token Index: 674

Text #6

Max Range: 0.2756. Min Range: -0.2756

Max Act: 0.2439. Min Act: -0.0003

Data Index: 886622 (C4 (Web Text))

Max Activating Token Index: 364

Text #7

Max Range: 0.2756. Min Range: -0.2756

Max Act: 0.2435. Min Act: -0.0003

Data Index: 391008 (C4 (Web Text))

Max Activating Token Index: 774

Text #8

Max Range: 0.2756. Min Range: -0.2756

Max Act: 0.2426. Min Act: -0.0002

Data Index: 1222353 (C4 (Web Text))

Max Activating Token Index: 82

Text #9

Max Range: 0.2756. Min Range: -0.2756

Max Act: 0.2403. Min Act: -0.0003

Data Index: 1148605 (C4 (Web Text))

Max Activating Token Index: 208

Text #10

Max Range: 0.2756. Min Range: -0.2756

Max Act: 0.2381. Min Act: -0.0003

Data Index: 274903 (C4 (Web Text))

Max Activating Token Index: 739

Text #11

Max Range: 0.2756. Min Range: -0.2756

Max Act: 0.2380. Min Act: -0.0003

Data Index: 325977 (C4 (Web Text))

Max Activating Token Index: 546

Text #12

Max Range: 0.2756. Min Range: -0.2756

Max Act: 0.2370. Min Act: -0.0003

Data Index: 1264947 (C4 (Web Text))

Max Activating Token Index: 957

Text #13

Max Range: 0.2756. Min Range: -0.2756

Max Act: 0.2363. Min Act: -0.0003

Data Index: 1306112 (C4 (Web Text))

Max Activating Token Index: 496

Text #14

Max Range: 0.2756. Min Range: -0.2756

Max Act: 0.2351. Min Act: -0.0003

Data Index: 741138 (C4 (Web Text))

Max Activating Token Index: 293

Text #15

Max Range: 0.2756. Min Range: -0.2756

Max Act: 0.2349. Min Act: -0.0003

Data Index: 872039 (C4 (Web Text))

Max Activating Token Index: 501

Text #16

Max Range: 0.2756. Min Range: -0.2756

Max Act: 0.2341. Min Act: -0.0003

Data Index: 912178 (C4 (Web Text))

Max Activating Token Index: 127

Text #17

Max Range: 0.2756. Min Range: -0.2756

Max Act: 0.2335. Min Act: -0.0003

Data Index: 455167 (C4 (Web Text))

Max Activating Token Index: 589

Text #18

Max Range: 0.2756. Min Range: -0.2756

Max Act: 0.2317. Min Act: -0.0003

Data Index: 344582 (C4 (Web Text))

Max Activating Token Index: 97

Text #19

Max Range: 0.2756. Min Range: -0.2756

Max Act: 0.2301. Min Act: -0.0003

Data Index: 1042826 (C4 (Web Text))

Max Activating Token Index: 261