Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3823 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 8.1173. Min Range: -8.1173

Max Act: 8.1173. Min Act: -0.0000

Data Index: 832443 (C4 (Web Text))

Max Activating Token Index: 186

Text #1

Max Range: 8.1173. Min Range: -8.1173

Max Act: 7.9016. Min Act: -0.0000

Data Index: 30762 (C4 (Web Text))

Max Activating Token Index: 535

Text #2

Max Range: 8.1173. Min Range: -8.1173

Max Act: 7.6056. Min Act: -0.0000

Data Index: 1345916 (C4 (Web Text))

Max Activating Token Index: 469

Text #3

Max Range: 8.1173. Min Range: -8.1173

Max Act: 7.5300. Min Act: -0.0000

Data Index: 704835 (C4 (Web Text))

Max Activating Token Index: 999

Text #4

Max Range: 8.1173. Min Range: -8.1173

Max Act: 8.0024. Min Act: -0.0000

Data Index: 1128140 (C4 (Web Text))

Max Activating Token Index: 333

Text #5

Max Range: 8.1173. Min Range: -8.1173

Max Act: 7.1004. Min Act: -0.0000

Data Index: 183665 (C4 (Web Text))

Max Activating Token Index: 666

Text #6

Max Range: 8.1173. Min Range: -8.1173

Max Act: 7.2408. Min Act: -0.0000

Data Index: 1276407 (C4 (Web Text))

Max Activating Token Index: 412

Text #7

Max Range: 8.1173. Min Range: -8.1173

Max Act: 6.6605. Min Act: -0.0000

Data Index: 246892 (C4 (Web Text))

Max Activating Token Index: 983

Text #8

Max Range: 8.1173. Min Range: -8.1173

Max Act: 6.9830. Min Act: -0.0000

Data Index: 219285 (C4 (Web Text))

Max Activating Token Index: 957

Text #9

Max Range: 8.1173. Min Range: -8.1173

Max Act: 6.2925. Min Act: -0.0000

Data Index: 924477 (C4 (Web Text))

Max Activating Token Index: 317

Text #10

Max Range: 8.1173. Min Range: -8.1173

Max Act: 5.6975. Min Act: -0.0000

Data Index: 410146 (C4 (Web Text))

Max Activating Token Index: 325

Text #11

Max Range: 8.1173. Min Range: -8.1173

Max Act: 5.5735. Min Act: -0.0000

Data Index: 882405 (C4 (Web Text))

Max Activating Token Index: 201

Text #12

Max Range: 8.1173. Min Range: -8.1173

Max Act: 5.4702. Min Act: -0.0000

Data Index: 1303097 (C4 (Web Text))

Max Activating Token Index: 601

Text #13

Max Range: 8.1173. Min Range: -8.1173

Max Act: 5.2288. Min Act: -0.0000

Data Index: 61617 (C4 (Web Text))

Max Activating Token Index: 30

Text #14

Max Range: 8.1173. Min Range: -8.1173

Max Act: 5.5421. Min Act: -0.0000

Data Index: 775023 (C4 (Web Text))

Max Activating Token Index: 662

Text #15

Max Range: 8.1173. Min Range: -8.1173

Max Act: 5.6368. Min Act: -0.0000

Data Index: 1078715 (C4 (Web Text))

Max Activating Token Index: 751

Text #16

Max Range: 8.1173. Min Range: -8.1173

Max Act: 5.4470. Min Act: -0.0000

Data Index: 691999 (C4 (Web Text))

Max Activating Token Index: 434

Text #17

Max Range: 8.1173. Min Range: -8.1173

Max Act: 5.7364. Min Act: -0.0000

Data Index: 849651 (C4 (Web Text))

Max Activating Token Index: 416

Text #18

Max Range: 8.1173. Min Range: -8.1173

Max Act: 5.3792. Min Act: -0.0000

Data Index: 682739 (C4 (Web Text))

Max Activating Token Index: 24

Text #19

Max Range: 8.1173. Min Range: -8.1173

Max Act: 5.7459. Min Act: -0.0000

Data Index: 1048295 (C4 (Web Text))

Max Activating Token Index: 297