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

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

Neuron 3673 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0464. Min Act: -0.0000

Data Index: 718013 (C4 (Web Text))

Max Activating Token Index: 258

Text #1

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0403. Min Act: -0.0000

Data Index: 425829 (C4 (Web Text))

Max Activating Token Index: 100

Text #2

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0383. Min Act: -0.0000

Data Index: 789340 (C4 (Web Text))

Max Activating Token Index: 412

Text #3

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0378. Min Act: -0.0000

Data Index: 301737 (C4 (Web Text))

Max Activating Token Index: 306

Text #4

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0341. Min Act: -0.0000

Data Index: 538913 (C4 (Web Text))

Max Activating Token Index: 289

Text #5

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0368. Min Act: -0.0000

Data Index: 830281 (C4 (Web Text))

Max Activating Token Index: 792

Text #6

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0331. Min Act: -0.0000

Data Index: 74559 (C4 (Web Text))

Max Activating Token Index: 917

Text #7

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0329. Min Act: -0.0000

Data Index: 1027530 (C4 (Web Text))

Max Activating Token Index: 578

Text #8

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0325. Min Act: -0.0000

Data Index: 596157 (C4 (Web Text))

Max Activating Token Index: 696

Text #9

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0342. Min Act: -0.0000

Data Index: 128545 (C4 (Web Text))

Max Activating Token Index: 567

Text #10

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0300. Min Act: -0.0000

Data Index: 133903 (C4 (Web Text))

Max Activating Token Index: 382

Text #11

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0324. Min Act: -0.0000

Data Index: 724795 (C4 (Web Text))

Max Activating Token Index: 735

Text #12

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0319. Min Act: -0.0000

Data Index: 1213230 (C4 (Web Text))

Max Activating Token Index: 967

Text #13

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0331. Min Act: -0.0000

Data Index: 85596 (C4 (Web Text))

Max Activating Token Index: 326

Text #14

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0328. Min Act: -0.0000

Data Index: 491382 (C4 (Web Text))

Max Activating Token Index: 17

Text #15

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0287. Min Act: -0.0000

Data Index: 463065 (C4 (Web Text))

Max Activating Token Index: 558

Text #16

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0320. Min Act: -0.0000

Data Index: 914662 (C4 (Web Text))

Max Activating Token Index: 707

Text #17

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0309. Min Act: -0.0000

Data Index: 745298 (C4 (Web Text))

Max Activating Token Index: 893

Text #18

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0310. Min Act: -0.0000

Data Index: 427620 (C4 (Web Text))

Max Activating Token Index: 880

Text #19

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0310. Min Act: -0.0000

Data Index: 503050 (C4 (Web Text))

Max Activating Token Index: 580