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

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

Neuron 5087 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: 0.6671. Min Range: -0.6671

Max Act: 0.6671. Min Act: -0.0000

Data Index: 135817 (C4 (Web Text))

Max Activating Token Index: 687

Text #1

Max Range: 0.6671. Min Range: -0.6671

Max Act: 0.6206. Min Act: -0.0000

Data Index: 1174127 (C4 (Web Text))

Max Activating Token Index: 615

Text #2

Max Range: 0.6671. Min Range: -0.6671

Max Act: 0.6159. Min Act: -0.0000

Data Index: 460917 (C4 (Web Text))

Max Activating Token Index: 459

Text #3

Max Range: 0.6671. Min Range: -0.6671

Max Act: 0.5839. Min Act: -0.0000

Data Index: 659163 (C4 (Web Text))

Max Activating Token Index: 119

Text #4

Max Range: 0.6671. Min Range: -0.6671

Max Act: 0.6002. Min Act: -0.0000

Data Index: 325713 (C4 (Web Text))

Max Activating Token Index: 183

Text #5

Max Range: 0.6671. Min Range: -0.6671

Max Act: 0.5613. Min Act: -0.0000

Data Index: 1178976 (C4 (Web Text))

Max Activating Token Index: 357

Text #6

Max Range: 0.6671. Min Range: -0.6671

Max Act: 0.5076. Min Act: -0.0000

Data Index: 1065974 (C4 (Web Text))

Max Activating Token Index: 345

Text #7

Max Range: 0.6671. Min Range: -0.6671

Max Act: 0.5265. Min Act: -0.0000

Data Index: 1282622 (C4 (Web Text))

Max Activating Token Index: 100

Text #8

Max Range: 0.6671. Min Range: -0.6671

Max Act: 0.5240. Min Act: -0.0000

Data Index: 531772 (C4 (Web Text))

Max Activating Token Index: 764

Text #9

Max Range: 0.6671. Min Range: -0.6671

Max Act: 0.5170. Min Act: -0.0000

Data Index: 11553 (C4 (Web Text))

Max Activating Token Index: 740

Text #10

Max Range: 0.6671. Min Range: -0.6671

Max Act: 0.5092. Min Act: -0.0000

Data Index: 1215845 (C4 (Web Text))

Max Activating Token Index: 649

Text #11

Max Range: 0.6671. Min Range: -0.6671

Max Act: 0.4981. Min Act: -0.0000

Data Index: 1014077 (C4 (Web Text))

Max Activating Token Index: 33

Text #12

Max Range: 0.6671. Min Range: -0.6671

Max Act: 0.5114. Min Act: -0.0000

Data Index: 548426 (C4 (Web Text))

Max Activating Token Index: 658

Text #13

Max Range: 0.6671. Min Range: -0.6671

Max Act: 0.5273. Min Act: -0.0000

Data Index: 1173296 (C4 (Web Text))

Max Activating Token Index: 918

Text #14

Max Range: 0.6671. Min Range: -0.6671

Max Act: 0.4860. Min Act: -0.0000

Data Index: 1345571 (C4 (Web Text))

Max Activating Token Index: 658

Text #15

Max Range: 0.6671. Min Range: -0.6671

Max Act: 0.4677. Min Act: -0.0000

Data Index: 694917 (C4 (Web Text))

Max Activating Token Index: 196

Text #16

Max Range: 0.6671. Min Range: -0.6671

Max Act: 0.4377. Min Act: -0.0000

Data Index: 306835 (C4 (Web Text))

Max Activating Token Index: 819

Text #17

Max Range: 0.6671. Min Range: -0.6671

Max Act: 0.4650. Min Act: -0.0000

Data Index: 617254 (C4 (Web Text))

Max Activating Token Index: 106

Text #18

Max Range: 0.6671. Min Range: -0.6671

Max Act: 0.4369. Min Act: -0.0000

Data Index: 701133 (C4 (Web Text))

Max Activating Token Index: 97

Text #19

Max Range: 0.6671. Min Range: -0.6671

Max Act: 0.4559. Min Act: -0.0000

Data Index: 1149468 (C4 (Web Text))

Max Activating Token Index: 606