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

Dataset: The Pile

Neuron 2214 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5426. Min Range: -0.5426

Max Act: 0.5426. Min Act: -0.0000

Data Index: 1286701 (The Pile)

Max Activating Token Index: 126

Text #1

Max Range: 0.5426. Min Range: -0.5426

Max Act: 0.5335. Min Act: -0.0000

Data Index: 1243022 (The Pile)

Max Activating Token Index: 289

Text #2

Max Range: 0.5426. Min Range: -0.5426

Max Act: 0.5178. Min Act: -0.0000

Data Index: 1390315 (The Pile)

Max Activating Token Index: 241

Text #3

Max Range: 0.5426. Min Range: -0.5426

Max Act: 0.5273. Min Act: -0.0000

Data Index: 399220 (The Pile)

Max Activating Token Index: 21

Text #4

Max Range: 0.5426. Min Range: -0.5426

Max Act: 0.5280. Min Act: -0.0000

Data Index: 662790 (The Pile)

Max Activating Token Index: 391

Text #5

Max Range: 0.5426. Min Range: -0.5426

Max Act: 0.4788. Min Act: -0.0000

Data Index: 976945 (The Pile)

Max Activating Token Index: 1014

Text #6

Max Range: 0.5426. Min Range: -0.5426

Max Act: 0.5355. Min Act: -0.0000

Data Index: 1678342 (The Pile)

Max Activating Token Index: 500

Text #7

Max Range: 0.5426. Min Range: -0.5426

Max Act: 0.5086. Min Act: -0.0000

Data Index: 311713 (The Pile)

Max Activating Token Index: 52

Text #8

Max Range: 0.5426. Min Range: -0.5426

Max Act: 0.5090. Min Act: -0.0000

Data Index: 132654 (The Pile)

Max Activating Token Index: 862

Text #9

Max Range: 0.5426. Min Range: -0.5426

Max Act: 0.4899. Min Act: -0.0000

Data Index: 1276122 (The Pile)

Max Activating Token Index: 385

Text #10

Max Range: 0.5426. Min Range: -0.5426

Max Act: 0.4715. Min Act: -0.0000

Data Index: 14833 (The Pile)

Max Activating Token Index: 136

Text #11

Max Range: 0.5426. Min Range: -0.5426

Max Act: 0.4614. Min Act: -0.0000

Data Index: 1779256 (The Pile)

Max Activating Token Index: 312

Text #12

Max Range: 0.5426. Min Range: -0.5426

Max Act: 0.5171. Min Act: -0.0000

Data Index: 1331621 (The Pile)

Max Activating Token Index: 227

Text #13

Max Range: 0.5426. Min Range: -0.5426

Max Act: 0.4188. Min Act: -0.0000

Data Index: 655346 (The Pile)

Max Activating Token Index: 210

Text #14

Max Range: 0.5426. Min Range: -0.5426

Max Act: 0.4813. Min Act: -0.0000

Data Index: 41039 (The Pile)

Max Activating Token Index: 184

Text #15

Max Range: 0.5426. Min Range: -0.5426

Max Act: 0.4353. Min Act: -0.0000

Data Index: 853783 (The Pile)

Max Activating Token Index: 1019

Text #16

Max Range: 0.5426. Min Range: -0.5426

Max Act: 0.4886. Min Act: -0.0000

Data Index: 1756255 (The Pile)

Max Activating Token Index: 28

Text #17

Max Range: 0.5426. Min Range: -0.5426

Max Act: 0.4376. Min Act: -0.0000

Data Index: 1515984 (The Pile)

Max Activating Token Index: 38

Text #18

Max Range: 0.5426. Min Range: -0.5426

Max Act: 0.4125. Min Act: -0.0000

Data Index: 514791 (The Pile)

Max Activating Token Index: 711

Text #19

Max Range: 0.5426. Min Range: -0.5426

Max Act: 0.3605. Min Act: -0.0000

Data Index: 222647 (The Pile)

Max Activating Token Index: 1022