Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1156 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2772. Min Act: -0.0000

Data Index: 1017154 (The Pile)

Max Activating Token Index: 859

Text #1

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2652. Min Act: -0.0000

Data Index: 276889 (The Pile)

Max Activating Token Index: 921

Text #2

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2516. Min Act: -0.0000

Data Index: 1345509 (The Pile)

Max Activating Token Index: 109

Text #3

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2409. Min Act: -0.0000

Data Index: 37504 (The Pile)

Max Activating Token Index: 354

Text #4

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2449. Min Act: -0.0000

Data Index: 724198 (The Pile)

Max Activating Token Index: 885

Text #5

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2603. Min Act: -0.0000

Data Index: 1214186 (The Pile)

Max Activating Token Index: 955

Text #6

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2364. Min Act: -0.0000

Data Index: 707173 (The Pile)

Max Activating Token Index: 52

Text #7

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2423. Min Act: -0.0000

Data Index: 1785869 (The Pile)

Max Activating Token Index: 473

Text #8

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2186. Min Act: -0.0000

Data Index: 502643 (The Pile)

Max Activating Token Index: 617

Text #9

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2488. Min Act: -0.0000

Data Index: 1589377 (The Pile)

Max Activating Token Index: 819

Text #10

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2166. Min Act: -0.0000

Data Index: 1822747 (The Pile)

Max Activating Token Index: 973

Text #11

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2210. Min Act: -0.0000

Data Index: 1688117 (The Pile)

Max Activating Token Index: 746

Text #12

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2062. Min Act: -0.0000

Data Index: 1167807 (The Pile)

Max Activating Token Index: 358

Text #13

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2161. Min Act: -0.0000

Data Index: 1693003 (The Pile)

Max Activating Token Index: 64

Text #14

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2213. Min Act: -0.0000

Data Index: 1446110 (The Pile)

Max Activating Token Index: 227

Text #15

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2064. Min Act: -0.0000

Data Index: 1814428 (The Pile)

Max Activating Token Index: 186

Text #16

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2202. Min Act: -0.0000

Data Index: 1978800 (The Pile)

Max Activating Token Index: 328

Text #17

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2190. Min Act: -0.0000

Data Index: 309959 (The Pile)

Max Activating Token Index: 402

Text #18

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2268. Min Act: -0.0000

Data Index: 919148 (The Pile)

Max Activating Token Index: 719

Text #19

Max Range: 0.2772. Min Range: -0.2772

Max Act: 0.2207. Min Act: -0.0000

Data Index: 644030 (The Pile)

Max Activating Token Index: 633