Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 908 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 1.2347. Min Range: -1.2347

Max Act: 1.2347. Min Act: 0.0001

Data Index: 913420 (The Pile)

Max Activating Token Index: 9

Text #1

Max Range: 1.2347. Min Range: -1.2347

Max Act: 1.2193. Min Act: 0.0000

Data Index: 1680949 (The Pile)

Max Activating Token Index: 365

Text #2

Max Range: 1.2347. Min Range: -1.2347

Max Act: 1.2220. Min Act: -0.0000

Data Index: 933120 (The Pile)

Max Activating Token Index: 379

Text #3

Max Range: 1.2347. Min Range: -1.2347

Max Act: 1.1466. Min Act: 0.0001

Data Index: 1457643 (The Pile)

Max Activating Token Index: 745

Text #4

Max Range: 1.2347. Min Range: -1.2347

Max Act: 1.1087. Min Act: -0.0000

Data Index: 1968909 (The Pile)

Max Activating Token Index: 945

Text #5

Max Range: 1.2347. Min Range: -1.2347

Max Act: 1.1021. Min Act: -0.0000

Data Index: 1162564 (The Pile)

Max Activating Token Index: 621

Text #6

Max Range: 1.2347. Min Range: -1.2347

Max Act: 1.1401. Min Act: -0.0000

Data Index: 314319 (The Pile)

Max Activating Token Index: 743

Text #7

Max Range: 1.2347. Min Range: -1.2347

Max Act: 1.1047. Min Act: -0.0001

Data Index: 522179 (The Pile)

Max Activating Token Index: 411

Text #8

Max Range: 1.2347. Min Range: -1.2347

Max Act: 1.0964. Min Act: -0.0000

Data Index: 1582517 (The Pile)

Max Activating Token Index: 68

Text #9

Max Range: 1.2347. Min Range: -1.2347

Max Act: 1.1343. Min Act: -0.0000

Data Index: 1793195 (The Pile)

Max Activating Token Index: 41

Text #10

Max Range: 1.2347. Min Range: -1.2347

Max Act: 1.0297. Min Act: 0.0000

Data Index: 1153299 (The Pile)

Max Activating Token Index: 341

Text #11

Max Range: 1.2347. Min Range: -1.2347

Max Act: 1.0817. Min Act: -0.0000

Data Index: 663621 (The Pile)

Max Activating Token Index: 484

Text #12

Max Range: 1.2347. Min Range: -1.2347

Max Act: 1.1032. Min Act: 0.0000

Data Index: 1384227 (The Pile)

Max Activating Token Index: 42

Text #13

Max Range: 1.2347. Min Range: -1.2347

Max Act: 1.0247. Min Act: -0.0000

Data Index: 1380068 (The Pile)

Max Activating Token Index: 856

Text #14

Max Range: 1.2347. Min Range: -1.2347

Max Act: 1.0543. Min Act: -0.0000

Data Index: 1867155 (The Pile)

Max Activating Token Index: 9

Text #15

Max Range: 1.2347. Min Range: -1.2347

Max Act: 1.0211. Min Act: -0.0000

Data Index: 1891231 (The Pile)

Max Activating Token Index: 739

Text #16

Max Range: 1.2347. Min Range: -1.2347

Max Act: 1.0429. Min Act: -0.0000

Data Index: 258736 (The Pile)

Max Activating Token Index: 8

Text #17

Max Range: 1.2347. Min Range: -1.2347

Max Act: 1.0083. Min Act: -0.0000

Data Index: 1712766 (The Pile)

Max Activating Token Index: 22

Text #18

Max Range: 1.2347. Min Range: -1.2347

Max Act: 1.0367. Min Act: 0.0001

Data Index: 928805 (The Pile)

Max Activating Token Index: 8

Text #19

Max Range: 1.2347. Min Range: -1.2347

Max Act: 1.0376. Min Act: -0.0000

Data Index: 1461924 (The Pile)

Max Activating Token Index: 507