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

Dataset: The Pile

Neuron 433 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.5212. Min Range: -1.5212

Max Act: 1.5212. Min Act: -0.0000

Data Index: 549747 (The Pile)

Max Activating Token Index: 959

Text #1

Max Range: 1.5212. Min Range: -1.5212

Max Act: 1.3964. Min Act: -0.0000

Data Index: 89653 (The Pile)

Max Activating Token Index: 951

Text #2

Max Range: 1.5212. Min Range: -1.5212

Max Act: 1.2937. Min Act: -0.0000

Data Index: 280626 (The Pile)

Max Activating Token Index: 547

Text #3

Max Range: 1.5212. Min Range: -1.5212

Max Act: 1.2295. Min Act: -0.0000

Data Index: 1525293 (The Pile)

Max Activating Token Index: 795

Text #4

Max Range: 1.5212. Min Range: -1.5212

Max Act: 1.2923. Min Act: -0.0000

Data Index: 1151519 (The Pile)

Max Activating Token Index: 822

Text #5

Max Range: 1.5212. Min Range: -1.5212

Max Act: 1.1297. Min Act: -0.0000

Data Index: 768085 (The Pile)

Max Activating Token Index: 907

Text #6

Max Range: 1.5212. Min Range: -1.5212

Max Act: 1.2628. Min Act: -0.0000

Data Index: 1918834 (The Pile)

Max Activating Token Index: 367

Text #7

Max Range: 1.5212. Min Range: -1.5212

Max Act: 1.2370. Min Act: -0.0000

Data Index: 1845015 (The Pile)

Max Activating Token Index: 612

Text #8

Max Range: 1.5212. Min Range: -1.5212

Max Act: 1.2871. Min Act: -0.0000

Data Index: 548857 (The Pile)

Max Activating Token Index: 943

Text #9

Max Range: 1.5212. Min Range: -1.5212

Max Act: 1.1418. Min Act: -0.0000

Data Index: 751867 (The Pile)

Max Activating Token Index: 282

Text #10

Max Range: 1.5212. Min Range: -1.5212

Max Act: 1.1250. Min Act: -0.0000

Data Index: 1643920 (The Pile)

Max Activating Token Index: 998

Text #11

Max Range: 1.5212. Min Range: -1.5212

Max Act: 1.1649. Min Act: -0.0000

Data Index: 111778 (The Pile)

Max Activating Token Index: 498

Text #12

Max Range: 1.5212. Min Range: -1.5212

Max Act: 1.1038. Min Act: -0.0000

Data Index: 441131 (The Pile)

Max Activating Token Index: 935

Text #13

Max Range: 1.5212. Min Range: -1.5212

Max Act: 1.0861. Min Act: -0.0000

Data Index: 393142 (The Pile)

Max Activating Token Index: 801

Text #14

Max Range: 1.5212. Min Range: -1.5212

Max Act: 1.0818. Min Act: -0.0000

Data Index: 611707 (The Pile)

Max Activating Token Index: 27

Text #15

Max Range: 1.5212. Min Range: -1.5212

Max Act: 1.0689. Min Act: -0.0000

Data Index: 1959131 (The Pile)

Max Activating Token Index: 987

Text #16

Max Range: 1.5212. Min Range: -1.5212

Max Act: 1.1386. Min Act: -0.0000

Data Index: 272323 (The Pile)

Max Activating Token Index: 355

Text #17

Max Range: 1.5212. Min Range: -1.5212

Max Act: 1.1881. Min Act: -0.0000

Data Index: 1776171 (The Pile)

Max Activating Token Index: 84

Text #18

Max Range: 1.5212. Min Range: -1.5212

Max Act: 1.1177. Min Act: -0.0000

Data Index: 1490880 (The Pile)

Max Activating Token Index: 897

Text #19

Max Range: 1.5212. Min Range: -1.5212

Max Act: 1.1257. Min Act: -0.0000

Data Index: 732700 (The Pile)

Max Activating Token Index: 221