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

Dataset: The Pile

Neuron 4155 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5198. Min Range: -1.5198

Max Act: 1.2769. Min Act: -0.0001

Data Index: 1188834 (The Pile)

Max Activating Token Index: 136

Text #1

Max Range: 1.5198. Min Range: -1.5198

Max Act: 1.5198. Min Act: -0.0000

Data Index: 372329 (The Pile)

Max Activating Token Index: 942

Text #2

Max Range: 1.5198. Min Range: -1.5198

Max Act: 1.1472. Min Act: -0.0000

Data Index: 1428181 (The Pile)

Max Activating Token Index: 707

Text #3

Max Range: 1.5198. Min Range: -1.5198

Max Act: 1.3363. Min Act: -0.0000

Data Index: 1156232 (The Pile)

Max Activating Token Index: 789

Text #4

Max Range: 1.5198. Min Range: -1.5198

Max Act: 1.1988. Min Act: -0.0000

Data Index: 1373283 (The Pile)

Max Activating Token Index: 1016

Text #5

Max Range: 1.5198. Min Range: -1.5198

Max Act: 1.1063. Min Act: -0.0000

Data Index: 1851133 (The Pile)

Max Activating Token Index: 305

Text #6

Max Range: 1.5198. Min Range: -1.5198

Max Act: 1.2399. Min Act: -0.0000

Data Index: 1974402 (The Pile)

Max Activating Token Index: 806

Text #7

Max Range: 1.5198. Min Range: -1.5198

Max Act: 1.1142. Min Act: -0.0000

Data Index: 727046 (The Pile)

Max Activating Token Index: 480

Text #8

Max Range: 1.5198. Min Range: -1.5198

Max Act: 1.3317. Min Act: -0.0000

Data Index: 1891389 (The Pile)

Max Activating Token Index: 609

Text #9

Max Range: 1.5198. Min Range: -1.5198

Max Act: 1.2352. Min Act: -0.0000

Data Index: 1638886 (The Pile)

Max Activating Token Index: 819

Text #10

Max Range: 1.5198. Min Range: -1.5198

Max Act: 1.1594. Min Act: -0.0000

Data Index: 209130 (The Pile)

Max Activating Token Index: 562

Text #11

Max Range: 1.5198. Min Range: -1.5198

Max Act: 1.1287. Min Act: -0.0000

Data Index: 1598119 (The Pile)

Max Activating Token Index: 480

Text #12

Max Range: 1.5198. Min Range: -1.5198

Max Act: 1.1416. Min Act: -0.0000

Data Index: 235449 (The Pile)

Max Activating Token Index: 458

Text #13

Max Range: 1.5198. Min Range: -1.5198

Max Act: 1.1387. Min Act: -0.0000

Data Index: 1049574 (The Pile)

Max Activating Token Index: 587

Text #14

Max Range: 1.5198. Min Range: -1.5198

Max Act: 1.2068. Min Act: -0.0000

Data Index: 1102975 (The Pile)

Max Activating Token Index: 943

Text #15

Max Range: 1.5198. Min Range: -1.5198

Max Act: 1.0767. Min Act: -0.0000

Data Index: 1414088 (The Pile)

Max Activating Token Index: 329

Text #16

Max Range: 1.5198. Min Range: -1.5198

Max Act: 1.0946. Min Act: -0.0000

Data Index: 443368 (The Pile)

Max Activating Token Index: 13

Text #17

Max Range: 1.5198. Min Range: -1.5198

Max Act: 1.1179. Min Act: -0.0000

Data Index: 1207610 (The Pile)

Max Activating Token Index: 507

Text #18

Max Range: 1.5198. Min Range: -1.5198

Max Act: 1.0788. Min Act: -0.0000

Data Index: 1876323 (The Pile)

Max Activating Token Index: 229

Text #19

Max Range: 1.5198. Min Range: -1.5198

Max Act: 0.9984. Min Act: -0.0000

Data Index: 1082029 (The Pile)

Max Activating Token Index: 881