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

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

Neuron 2161 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9161. Min Range: -1.9161

Max Act: 1.9161. Min Act: -0.0000

Data Index: 1133260 (C4 (Web Text))

Max Activating Token Index: 539

Text #1

Max Range: 1.9161. Min Range: -1.9161

Max Act: 1.6193. Min Act: -0.0000

Data Index: 103867 (C4 (Web Text))

Max Activating Token Index: 18

Text #2

Max Range: 1.9161. Min Range: -1.9161

Max Act: 1.5082. Min Act: -0.0000

Data Index: 1327845 (C4 (Web Text))

Max Activating Token Index: 467

Text #3

Max Range: 1.9161. Min Range: -1.9161

Max Act: 1.3998. Min Act: -0.0000

Data Index: 756949 (C4 (Web Text))

Max Activating Token Index: 527

Text #4

Max Range: 1.9161. Min Range: -1.9161

Max Act: 1.4812. Min Act: -0.0000

Data Index: 1291936 (C4 (Web Text))

Max Activating Token Index: 613

Text #5

Max Range: 1.9161. Min Range: -1.9161

Max Act: 1.4729. Min Act: -0.0000

Data Index: 32074 (C4 (Web Text))

Max Activating Token Index: 498

Text #6

Max Range: 1.9161. Min Range: -1.9161

Max Act: 1.3886. Min Act: -0.0000

Data Index: 173104 (C4 (Web Text))

Max Activating Token Index: 24

Text #7

Max Range: 1.9161. Min Range: -1.9161

Max Act: 1.4490. Min Act: -0.0000

Data Index: 696611 (C4 (Web Text))

Max Activating Token Index: 1004

Text #8

Max Range: 1.9161. Min Range: -1.9161

Max Act: 1.4470. Min Act: -0.0000

Data Index: 400908 (C4 (Web Text))

Max Activating Token Index: 89

Text #9

Max Range: 1.9161. Min Range: -1.9161

Max Act: 1.4102. Min Act: -0.0000

Data Index: 1150909 (C4 (Web Text))

Max Activating Token Index: 906

Text #10

Max Range: 1.9161. Min Range: -1.9161

Max Act: 1.4085. Min Act: -0.0000

Data Index: 1107458 (C4 (Web Text))

Max Activating Token Index: 453

Text #11

Max Range: 1.9161. Min Range: -1.9161

Max Act: 1.4868. Min Act: -0.0000

Data Index: 1257482 (C4 (Web Text))

Max Activating Token Index: 342

Text #12

Max Range: 1.9161. Min Range: -1.9161

Max Act: 1.3881. Min Act: -0.0000

Data Index: 16757 (C4 (Web Text))

Max Activating Token Index: 182

Text #13

Max Range: 1.9161. Min Range: -1.9161

Max Act: 1.3834. Min Act: -0.0000

Data Index: 518344 (C4 (Web Text))

Max Activating Token Index: 578

Text #14

Max Range: 1.9161. Min Range: -1.9161

Max Act: 1.3566. Min Act: -0.0000

Data Index: 224175 (C4 (Web Text))

Max Activating Token Index: 381

Text #15

Max Range: 1.9161. Min Range: -1.9161

Max Act: 1.3595. Min Act: -0.0000

Data Index: 1081289 (C4 (Web Text))

Max Activating Token Index: 540

Text #16

Max Range: 1.9161. Min Range: -1.9161

Max Act: 1.3342. Min Act: -0.0000

Data Index: 595030 (C4 (Web Text))

Max Activating Token Index: 173

Text #17

Max Range: 1.9161. Min Range: -1.9161

Max Act: 1.3312. Min Act: -0.0000

Data Index: 660716 (C4 (Web Text))

Max Activating Token Index: 962

Text #18

Max Range: 1.9161. Min Range: -1.9161

Max Act: 1.2523. Min Act: -0.0000

Data Index: 780648 (C4 (Web Text))

Max Activating Token Index: 308

Text #19

Max Range: 1.9161. Min Range: -1.9161

Max Act: 1.2213. Min Act: -0.0000

Data Index: 938472 (C4 (Web Text))

Max Activating Token Index: 636