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

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

Neuron 3477 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6191. Min Range: -0.6191

Max Act: 0.6191. Min Act: -0.0000

Data Index: 988900 (C4 (Web Text))

Max Activating Token Index: 715

Text #1

Max Range: 0.6191. Min Range: -0.6191

Max Act: 0.4856. Min Act: -0.0000

Data Index: 1559934 (Python Code)

Max Activating Token Index: 518

Text #2

Max Range: 0.6191. Min Range: -0.6191

Max Act: 0.4429. Min Act: -0.0000

Data Index: 1488324 (Python Code)

Max Activating Token Index: 712

Text #3

Max Range: 0.6191. Min Range: -0.6191

Max Act: 0.4239. Min Act: -0.0000

Data Index: 816065 (C4 (Web Text))

Max Activating Token Index: 39

Text #4

Max Range: 0.6191. Min Range: -0.6191

Max Act: 0.4870. Min Act: -0.0000

Data Index: 1624705 (Python Code)

Max Activating Token Index: 147

Text #5

Max Range: 0.6191. Min Range: -0.6191

Max Act: 0.4184. Min Act: -0.0000

Data Index: 159073 (C4 (Web Text))

Max Activating Token Index: 393

Text #6

Max Range: 0.6191. Min Range: -0.6191

Max Act: 0.4378. Min Act: -0.0000

Data Index: 1620136 (Python Code)

Max Activating Token Index: 461

Text #7

Max Range: 0.6191. Min Range: -0.6191

Max Act: 0.3943. Min Act: -0.0000

Data Index: 1293702 (C4 (Web Text))

Max Activating Token Index: 868

Text #8

Max Range: 0.6191. Min Range: -0.6191

Max Act: 0.3255. Min Act: -0.0000

Data Index: 613550 (C4 (Web Text))

Max Activating Token Index: 633

Text #9

Max Range: 0.6191. Min Range: -0.6191

Max Act: 0.3653. Min Act: -0.0000

Data Index: 128267 (C4 (Web Text))

Max Activating Token Index: 863

Text #10

Max Range: 0.6191. Min Range: -0.6191

Max Act: 0.3855. Min Act: -0.0000

Data Index: 1276734 (C4 (Web Text))

Max Activating Token Index: 898

Text #11

Max Range: 0.6191. Min Range: -0.6191

Max Act: 0.3355. Min Act: -0.0000

Data Index: 221611 (C4 (Web Text))

Max Activating Token Index: 602

Text #12

Max Range: 0.6191. Min Range: -0.6191

Max Act: 0.3383. Min Act: -0.0000

Data Index: 1040733 (C4 (Web Text))

Max Activating Token Index: 592

Text #13

Max Range: 0.6191. Min Range: -0.6191

Max Act: 0.3480. Min Act: -0.0000

Data Index: 420677 (C4 (Web Text))

Max Activating Token Index: 615

Text #14

Max Range: 0.6191. Min Range: -0.6191

Max Act: 0.3716. Min Act: -0.0000

Data Index: 873794 (C4 (Web Text))

Max Activating Token Index: 475

Text #15

Max Range: 0.6191. Min Range: -0.6191

Max Act: 0.3701. Min Act: -0.0000

Data Index: 1226275 (C4 (Web Text))

Max Activating Token Index: 169

Text #16

Max Range: 0.6191. Min Range: -0.6191

Max Act: 0.3648. Min Act: -0.0000

Data Index: 1154944 (C4 (Web Text))

Max Activating Token Index: 114

Text #17

Max Range: 0.6191. Min Range: -0.6191

Max Act: 0.3613. Min Act: -0.0000

Data Index: 816856 (C4 (Web Text))

Max Activating Token Index: 967

Text #18

Max Range: 0.6191. Min Range: -0.6191

Max Act: 0.3958. Min Act: -0.0000

Data Index: 1002693 (C4 (Web Text))

Max Activating Token Index: 822

Text #19

Max Range: 0.6191. Min Range: -0.6191

Max Act: 0.3549. Min Act: -0.0000

Data Index: 1056467 (C4 (Web Text))

Max Activating Token Index: 737