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

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

Neuron 3416 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6028. Min Range: -0.6028

Max Act: 0.6028. Min Act: -0.0001

Data Index: 658857 (C4 (Web Text))

Max Activating Token Index: 996

Text #1

Max Range: 0.6028. Min Range: -0.6028

Max Act: 0.4324. Min Act: -0.0001

Data Index: 895541 (C4 (Web Text))

Max Activating Token Index: 121

Text #2

Max Range: 0.6028. Min Range: -0.6028

Max Act: 0.4518. Min Act: -0.0001

Data Index: 194648 (C4 (Web Text))

Max Activating Token Index: 935

Text #3

Max Range: 0.6028. Min Range: -0.6028

Max Act: 0.3935. Min Act: -0.0001

Data Index: 874480 (C4 (Web Text))

Max Activating Token Index: 960

Text #4

Max Range: 0.6028. Min Range: -0.6028

Max Act: 0.4295. Min Act: -0.0001

Data Index: 49175 (C4 (Web Text))

Max Activating Token Index: 981

Text #5

Max Range: 0.6028. Min Range: -0.6028

Max Act: 0.4222. Min Act: -0.0001

Data Index: 102872 (C4 (Web Text))

Max Activating Token Index: 981

Text #6

Max Range: 0.6028. Min Range: -0.6028

Max Act: 0.4198. Min Act: -0.0001

Data Index: 567920 (C4 (Web Text))

Max Activating Token Index: 761

Text #7

Max Range: 0.6028. Min Range: -0.6028

Max Act: 0.3539. Min Act: -0.0001

Data Index: 375535 (C4 (Web Text))

Max Activating Token Index: 259

Text #8

Max Range: 0.6028. Min Range: -0.6028

Max Act: 0.3545. Min Act: -0.0001

Data Index: 1143971 (C4 (Web Text))

Max Activating Token Index: 662

Text #9

Max Range: 0.6028. Min Range: -0.6028

Max Act: 0.3837. Min Act: -0.0001

Data Index: 286536 (C4 (Web Text))

Max Activating Token Index: 1011

Text #10

Max Range: 0.6028. Min Range: -0.6028

Max Act: 0.3209. Min Act: -0.0001

Data Index: 996172 (C4 (Web Text))

Max Activating Token Index: 514

Text #11

Max Range: 0.6028. Min Range: -0.6028

Max Act: 0.3434. Min Act: -0.0001

Data Index: 498158 (C4 (Web Text))

Max Activating Token Index: 838

Text #12

Max Range: 0.6028. Min Range: -0.6028

Max Act: 0.3654. Min Act: -0.0001

Data Index: 853691 (C4 (Web Text))

Max Activating Token Index: 140

Text #13

Max Range: 0.6028. Min Range: -0.6028

Max Act: 0.3357. Min Act: -0.0001

Data Index: 7231 (C4 (Web Text))

Max Activating Token Index: 479

Text #14

Max Range: 0.6028. Min Range: -0.6028

Max Act: 0.3313. Min Act: -0.0001

Data Index: 297560 (C4 (Web Text))

Max Activating Token Index: 696

Text #15

Max Range: 0.6028. Min Range: -0.6028

Max Act: 0.3251. Min Act: -0.0001

Data Index: 1012838 (C4 (Web Text))

Max Activating Token Index: 497

Text #16

Max Range: 0.6028. Min Range: -0.6028

Max Act: 0.3443. Min Act: -0.0001

Data Index: 5430 (C4 (Web Text))

Max Activating Token Index: 798

Text #17

Max Range: 0.6028. Min Range: -0.6028

Max Act: 0.3340. Min Act: -0.0001

Data Index: 790480 (C4 (Web Text))

Max Activating Token Index: 661

Text #18

Max Range: 0.6028. Min Range: -0.6028

Max Act: 0.3327. Min Act: -0.0001

Data Index: 343637 (C4 (Web Text))

Max Activating Token Index: 765

Text #19

Max Range: 0.6028. Min Range: -0.6028

Max Act: 0.3436. Min Act: -0.0001

Data Index: 131828 (C4 (Web Text))

Max Activating Token Index: 572