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

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

Neuron 3826 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6842. Min Range: -0.6842

Max Act: 0.6842. Min Act: -0.0000

Data Index: 1349238 (C4 (Web Text))

Max Activating Token Index: 964

Text #1

Max Range: 0.6842. Min Range: -0.6842

Max Act: 0.4390. Min Act: -0.0000

Data Index: 697705 (C4 (Web Text))

Max Activating Token Index: 84

Text #2

Max Range: 0.6842. Min Range: -0.6842

Max Act: 0.3911. Min Act: -0.0000

Data Index: 729557 (C4 (Web Text))

Max Activating Token Index: 723

Text #3

Max Range: 0.6842. Min Range: -0.6842

Max Act: 0.3868. Min Act: -0.0000

Data Index: 1052512 (C4 (Web Text))

Max Activating Token Index: 128

Text #4

Max Range: 0.6842. Min Range: -0.6842

Max Act: 0.3857. Min Act: -0.0000

Data Index: 906700 (C4 (Web Text))

Max Activating Token Index: 623

Text #5

Max Range: 0.6842. Min Range: -0.6842

Max Act: 0.3447. Min Act: -0.0000

Data Index: 981962 (C4 (Web Text))

Max Activating Token Index: 798

Text #6

Max Range: 0.6842. Min Range: -0.6842

Max Act: 0.3396. Min Act: -0.0000

Data Index: 924371 (C4 (Web Text))

Max Activating Token Index: 953

Text #7

Max Range: 0.6842. Min Range: -0.6842

Max Act: 0.3471. Min Act: -0.0000

Data Index: 433972 (C4 (Web Text))

Max Activating Token Index: 445

Text #8

Max Range: 0.6842. Min Range: -0.6842

Max Act: 0.3439. Min Act: -0.0000

Data Index: 19927 (C4 (Web Text))

Max Activating Token Index: 825

Text #9

Max Range: 0.6842. Min Range: -0.6842

Max Act: 0.3462. Min Act: -0.0000

Data Index: 420687 (C4 (Web Text))

Max Activating Token Index: 789

Text #10

Max Range: 0.6842. Min Range: -0.6842

Max Act: 0.3330. Min Act: -0.0000

Data Index: 623928 (C4 (Web Text))

Max Activating Token Index: 599

Text #11

Max Range: 0.6842. Min Range: -0.6842

Max Act: 0.3246. Min Act: -0.0000

Data Index: 353449 (C4 (Web Text))

Max Activating Token Index: 595

Text #12

Max Range: 0.6842. Min Range: -0.6842

Max Act: 0.3315. Min Act: -0.0000

Data Index: 917245 (C4 (Web Text))

Max Activating Token Index: 703

Text #13

Max Range: 0.6842. Min Range: -0.6842

Max Act: 0.3201. Min Act: -0.0000

Data Index: 657283 (C4 (Web Text))

Max Activating Token Index: 70

Text #14

Max Range: 0.6842. Min Range: -0.6842

Max Act: 0.3171. Min Act: -0.0000

Data Index: 749324 (C4 (Web Text))

Max Activating Token Index: 62

Text #15

Max Range: 0.6842. Min Range: -0.6842

Max Act: 0.3255. Min Act: -0.0000

Data Index: 1441226 (Python Code)

Max Activating Token Index: 64

Text #16

Max Range: 0.6842. Min Range: -0.6842

Max Act: 0.3044. Min Act: -0.0000

Data Index: 843556 (C4 (Web Text))

Max Activating Token Index: 317

Text #17

Max Range: 0.6842. Min Range: -0.6842

Max Act: 0.3216. Min Act: -0.0000

Data Index: 1039971 (C4 (Web Text))

Max Activating Token Index: 772

Text #18

Max Range: 0.6842. Min Range: -0.6842

Max Act: 0.3112. Min Act: -0.0000

Data Index: 397469 (C4 (Web Text))

Max Activating Token Index: 628

Text #19

Max Range: 0.6842. Min Range: -0.6842

Max Act: 0.2984. Min Act: -0.0000

Data Index: 1310331 (C4 (Web Text))

Max Activating Token Index: 689