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

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

Neuron 4398 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: 0.1910. Min Range: -0.1910

Max Act: 0.1910. Min Act: -0.0000

Data Index: 953112 (C4 (Web Text))

Max Activating Token Index: 273

Text #1

Max Range: 0.1910. Min Range: -0.1910

Max Act: 0.1778. Min Act: -0.0000

Data Index: 326132 (C4 (Web Text))

Max Activating Token Index: 390

Text #2

Max Range: 0.1910. Min Range: -0.1910

Max Act: 0.1725. Min Act: -0.0000

Data Index: 354265 (C4 (Web Text))

Max Activating Token Index: 752

Text #3

Max Range: 0.1910. Min Range: -0.1910

Max Act: 0.1692. Min Act: -0.0000

Data Index: 291647 (C4 (Web Text))

Max Activating Token Index: 776

Text #4

Max Range: 0.1910. Min Range: -0.1910

Max Act: 0.1624. Min Act: -0.0000

Data Index: 1183715 (C4 (Web Text))

Max Activating Token Index: 386

Text #5

Max Range: 0.1910. Min Range: -0.1910

Max Act: 0.1512. Min Act: -0.0000

Data Index: 518107 (C4 (Web Text))

Max Activating Token Index: 66

Text #6

Max Range: 0.1910. Min Range: -0.1910

Max Act: 0.1442. Min Act: -0.0000

Data Index: 639307 (C4 (Web Text))

Max Activating Token Index: 749

Text #7

Max Range: 0.1910. Min Range: -0.1910

Max Act: 0.1532. Min Act: -0.0000

Data Index: 415473 (C4 (Web Text))

Max Activating Token Index: 150

Text #8

Max Range: 0.1910. Min Range: -0.1910

Max Act: 0.1500. Min Act: -0.0000

Data Index: 698354 (C4 (Web Text))

Max Activating Token Index: 975

Text #9

Max Range: 0.1910. Min Range: -0.1910

Max Act: 0.1326. Min Act: -0.0000

Data Index: 54157 (C4 (Web Text))

Max Activating Token Index: 622

Text #10

Max Range: 0.1910. Min Range: -0.1910

Max Act: 0.1263. Min Act: -0.0000

Data Index: 1205986 (C4 (Web Text))

Max Activating Token Index: 360

Text #11

Max Range: 0.1910. Min Range: -0.1910

Max Act: 0.1459. Min Act: -0.0000

Data Index: 1331633 (C4 (Web Text))

Max Activating Token Index: 757

Text #12

Max Range: 0.1910. Min Range: -0.1910

Max Act: 0.1418. Min Act: -0.0000

Data Index: 588880 (C4 (Web Text))

Max Activating Token Index: 950

Text #13

Max Range: 0.1910. Min Range: -0.1910

Max Act: 0.1322. Min Act: -0.0000

Data Index: 213369 (C4 (Web Text))

Max Activating Token Index: 993

Text #14

Max Range: 0.1910. Min Range: -0.1910

Max Act: 0.1085. Min Act: -0.0000

Data Index: 37281 (C4 (Web Text))

Max Activating Token Index: 599

Text #15

Max Range: 0.1910. Min Range: -0.1910

Max Act: 0.1237. Min Act: -0.0000

Data Index: 825929 (C4 (Web Text))

Max Activating Token Index: 336

Text #16

Max Range: 0.1910. Min Range: -0.1910

Max Act: 0.1244. Min Act: -0.0000

Data Index: 464754 (C4 (Web Text))

Max Activating Token Index: 556

Text #17

Max Range: 0.1910. Min Range: -0.1910

Max Act: 0.1169. Min Act: -0.0000

Data Index: 440478 (C4 (Web Text))

Max Activating Token Index: 42

Text #18

Max Range: 0.1910. Min Range: -0.1910

Max Act: 0.1190. Min Act: -0.0000

Data Index: 633447 (C4 (Web Text))

Max Activating Token Index: 70

Text #19

Max Range: 0.1910. Min Range: -0.1910

Max Act: 0.1161. Min Act: -0.0000

Data Index: 438158 (C4 (Web Text))

Max Activating Token Index: 973