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

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

Neuron 2982 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7175. Min Range: -4.7175

Max Act: 4.7175. Min Act: -0.0000

Data Index: 1354143 (C4 (Web Text))

Max Activating Token Index: 129

Text #1

Max Range: 4.7175. Min Range: -4.7175

Max Act: 3.6537. Min Act: 0.0001

Data Index: 889086 (C4 (Web Text))

Max Activating Token Index: 65

Text #2

Max Range: 4.7175. Min Range: -4.7175

Max Act: 3.4459. Min Act: -0.0000

Data Index: 1372957 (Python Code)

Max Activating Token Index: 953

Text #3

Max Range: 4.7175. Min Range: -4.7175

Max Act: 3.3976. Min Act: -0.0000

Data Index: 924860 (C4 (Web Text))

Max Activating Token Index: 730

Text #4

Max Range: 4.7175. Min Range: -4.7175

Max Act: 3.0119. Min Act: -0.0000

Data Index: 1365094 (Python Code)

Max Activating Token Index: 270

Text #5

Max Range: 4.7175. Min Range: -4.7175

Max Act: 3.3022. Min Act: -0.0000

Data Index: 756112 (C4 (Web Text))

Max Activating Token Index: 863

Text #6

Max Range: 4.7175. Min Range: -4.7175

Max Act: 2.8060. Min Act: -0.0000

Data Index: 44264 (C4 (Web Text))

Max Activating Token Index: 974

Text #7

Max Range: 4.7175. Min Range: -4.7175

Max Act: 2.9657. Min Act: -0.0000

Data Index: 951501 (C4 (Web Text))

Max Activating Token Index: 681

Text #8

Max Range: 4.7175. Min Range: -4.7175

Max Act: 2.8673. Min Act: -0.0000

Data Index: 1155115 (C4 (Web Text))

Max Activating Token Index: 899

Text #9

Max Range: 4.7175. Min Range: -4.7175

Max Act: 3.1846. Min Act: -0.0000

Data Index: 493470 (C4 (Web Text))

Max Activating Token Index: 423

Text #10

Max Range: 4.7175. Min Range: -4.7175

Max Act: 2.7134. Min Act: -0.0000

Data Index: 1480466 (Python Code)

Max Activating Token Index: 548

Text #11

Max Range: 4.7175. Min Range: -4.7175

Max Act: 2.0108. Min Act: -0.0000

Data Index: 68638 (C4 (Web Text))

Max Activating Token Index: 1015

Text #12

Max Range: 4.7175. Min Range: -4.7175

Max Act: 2.6156. Min Act: -0.0000

Data Index: 1513086 (Python Code)

Max Activating Token Index: 525

Text #13

Max Range: 4.7175. Min Range: -4.7175

Max Act: 2.7133. Min Act: -0.0000

Data Index: 643367 (C4 (Web Text))

Max Activating Token Index: 478

Text #14

Max Range: 4.7175. Min Range: -4.7175

Max Act: 2.2272. Min Act: -0.0000

Data Index: 1159967 (C4 (Web Text))

Max Activating Token Index: 453

Text #15

Max Range: 4.7175. Min Range: -4.7175

Max Act: 2.3468. Min Act: -0.0000

Data Index: 1641469 (Python Code)

Max Activating Token Index: 878

Text #16

Max Range: 4.7175. Min Range: -4.7175

Max Act: 2.3119. Min Act: -0.0000

Data Index: 30071 (C4 (Web Text))

Max Activating Token Index: 612

Text #17

Max Range: 4.7175. Min Range: -4.7175

Max Act: 2.2760. Min Act: -0.0000

Data Index: 1580439 (Python Code)

Max Activating Token Index: 787

Text #18

Max Range: 4.7175. Min Range: -4.7175

Max Act: 2.2773. Min Act: -0.0000

Data Index: 1087615 (C4 (Web Text))

Max Activating Token Index: 390

Text #19

Max Range: 4.7175. Min Range: -4.7175

Max Act: 2.0968. Min Act: -0.0000

Data Index: 169515 (C4 (Web Text))

Max Activating Token Index: 195