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

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

Neuron 2435 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: 1.5846. Min Range: -1.5846

Max Act: 1.5846. Min Act: -0.0001

Data Index: 524290 (C4 (Web Text))

Max Activating Token Index: 652

Text #1

Max Range: 1.5846. Min Range: -1.5846

Max Act: 1.1773. Min Act: -0.0000

Data Index: 668996 (C4 (Web Text))

Max Activating Token Index: 339

Text #2

Max Range: 1.5846. Min Range: -1.5846

Max Act: 1.0868. Min Act: -0.0001

Data Index: 1064462 (C4 (Web Text))

Max Activating Token Index: 257

Text #3

Max Range: 1.5846. Min Range: -1.5846

Max Act: 1.0792. Min Act: -0.0001

Data Index: 353127 (C4 (Web Text))

Max Activating Token Index: 230

Text #4

Max Range: 1.5846. Min Range: -1.5846

Max Act: 1.2212. Min Act: -0.0001

Data Index: 1201473 (C4 (Web Text))

Max Activating Token Index: 371

Text #5

Max Range: 1.5846. Min Range: -1.5846

Max Act: 1.1554. Min Act: -0.0001

Data Index: 695800 (C4 (Web Text))

Max Activating Token Index: 61

Text #6

Max Range: 1.5846. Min Range: -1.5846

Max Act: 1.1271. Min Act: -0.0000

Data Index: 673946 (C4 (Web Text))

Max Activating Token Index: 140

Text #7

Max Range: 1.5846. Min Range: -1.5846

Max Act: 1.0675. Min Act: -0.0000

Data Index: 341370 (C4 (Web Text))

Max Activating Token Index: 309

Text #8

Max Range: 1.5846. Min Range: -1.5846

Max Act: 1.0825. Min Act: -0.0001

Data Index: 46740 (C4 (Web Text))

Max Activating Token Index: 653

Text #9

Max Range: 1.5846. Min Range: -1.5846

Max Act: 1.0703. Min Act: -0.0001

Data Index: 406369 (C4 (Web Text))

Max Activating Token Index: 204

Text #10

Max Range: 1.5846. Min Range: -1.5846

Max Act: 1.1471. Min Act: -0.0001

Data Index: 669101 (C4 (Web Text))

Max Activating Token Index: 605

Text #11

Max Range: 1.5846. Min Range: -1.5846

Max Act: 1.1315. Min Act: -0.0001

Data Index: 681340 (C4 (Web Text))

Max Activating Token Index: 871

Text #12

Max Range: 1.5846. Min Range: -1.5846

Max Act: 1.0511. Min Act: -0.0001

Data Index: 512394 (C4 (Web Text))

Max Activating Token Index: 417

Text #13

Max Range: 1.5846. Min Range: -1.5846

Max Act: 0.9798. Min Act: -0.0001

Data Index: 356675 (C4 (Web Text))

Max Activating Token Index: 629

Text #14

Max Range: 1.5846. Min Range: -1.5846

Max Act: 1.1757. Min Act: -0.0000

Data Index: 1155838 (C4 (Web Text))

Max Activating Token Index: 615

Text #15

Max Range: 1.5846. Min Range: -1.5846

Max Act: 0.9882. Min Act: -0.0000

Data Index: 627998 (C4 (Web Text))

Max Activating Token Index: 816

Text #16

Max Range: 1.5846. Min Range: -1.5846

Max Act: 0.9793. Min Act: -0.0000

Data Index: 199919 (C4 (Web Text))

Max Activating Token Index: 256

Text #17

Max Range: 1.5846. Min Range: -1.5846

Max Act: 1.0016. Min Act: -0.0000

Data Index: 38823 (C4 (Web Text))

Max Activating Token Index: 165

Text #18

Max Range: 1.5846. Min Range: -1.5846

Max Act: 0.9564. Min Act: -0.0001

Data Index: 478473 (C4 (Web Text))

Max Activating Token Index: 385

Text #19

Max Range: 1.5846. Min Range: -1.5846

Max Act: 1.0209. Min Act: -0.0001

Data Index: 1291951 (C4 (Web Text))

Max Activating Token Index: 488