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

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

Neuron 164 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: 1.7682. Min Range: -1.7682

Max Act: 1.7682. Min Act: -0.0000

Data Index: 700936 (C4 (Web Text))

Max Activating Token Index: 258

Text #1

Max Range: 1.7682. Min Range: -1.7682

Max Act: 1.5703. Min Act: -0.0000

Data Index: 570063 (C4 (Web Text))

Max Activating Token Index: 998

Text #2

Max Range: 1.7682. Min Range: -1.7682

Max Act: 1.5637. Min Act: -0.0000

Data Index: 957562 (C4 (Web Text))

Max Activating Token Index: 5

Text #3

Max Range: 1.7682. Min Range: -1.7682

Max Act: 1.4286. Min Act: -0.0000

Data Index: 1274931 (C4 (Web Text))

Max Activating Token Index: 939

Text #4

Max Range: 1.7682. Min Range: -1.7682

Max Act: 1.3869. Min Act: -0.0000

Data Index: 1416525 (Python Code)

Max Activating Token Index: 313

Text #5

Max Range: 1.7682. Min Range: -1.7682

Max Act: 1.2917. Min Act: -0.0000

Data Index: 863399 (C4 (Web Text))

Max Activating Token Index: 874

Text #6

Max Range: 1.7682. Min Range: -1.7682

Max Act: 1.3590. Min Act: -0.0000

Data Index: 32376 (C4 (Web Text))

Max Activating Token Index: 565

Text #7

Max Range: 1.7682. Min Range: -1.7682

Max Act: 1.2534. Min Act: -0.0000

Data Index: 1603696 (Python Code)

Max Activating Token Index: 944

Text #8

Max Range: 1.7682. Min Range: -1.7682

Max Act: 1.2514. Min Act: -0.0000

Data Index: 1458319 (Python Code)

Max Activating Token Index: 725

Text #9

Max Range: 1.7682. Min Range: -1.7682

Max Act: 1.3961. Min Act: -0.0000

Data Index: 1395693 (Python Code)

Max Activating Token Index: 912

Text #10

Max Range: 1.7682. Min Range: -1.7682

Max Act: 1.2110. Min Act: -0.0000

Data Index: 517765 (C4 (Web Text))

Max Activating Token Index: 915

Text #11

Max Range: 1.7682. Min Range: -1.7682

Max Act: 1.1917. Min Act: -0.0000

Data Index: 108492 (C4 (Web Text))

Max Activating Token Index: 994

Text #12

Max Range: 1.7682. Min Range: -1.7682

Max Act: 1.1135. Min Act: -0.0000

Data Index: 1578655 (Python Code)

Max Activating Token Index: 606

Text #13

Max Range: 1.7682. Min Range: -1.7682

Max Act: 1.1686. Min Act: -0.0000

Data Index: 16821 (C4 (Web Text))

Max Activating Token Index: 240

Text #14

Max Range: 1.7682. Min Range: -1.7682

Max Act: 1.1105. Min Act: -0.0000

Data Index: 443980 (C4 (Web Text))

Max Activating Token Index: 486

Text #15

Max Range: 1.7682. Min Range: -1.7682

Max Act: 1.1152. Min Act: -0.0000

Data Index: 1253762 (C4 (Web Text))

Max Activating Token Index: 957

Text #16

Max Range: 1.7682. Min Range: -1.7682

Max Act: 1.1152. Min Act: -0.0000

Data Index: 1624383 (Python Code)

Max Activating Token Index: 307

Text #17

Max Range: 1.7682. Min Range: -1.7682

Max Act: 1.1112. Min Act: -0.0000

Data Index: 1644586 (Python Code)

Max Activating Token Index: 761

Text #18

Max Range: 1.7682. Min Range: -1.7682

Max Act: 1.2259. Min Act: -0.0000

Data Index: 610734 (C4 (Web Text))

Max Activating Token Index: 352

Text #19

Max Range: 1.7682. Min Range: -1.7682

Max Act: 1.1746. Min Act: -0.0000

Data Index: 702667 (C4 (Web Text))

Max Activating Token Index: 303