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

Dataset: The Pile

Neuron 3187 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8135. Min Range: -3.8135

Max Act: 3.8135. Min Act: -0.0000

Data Index: 199532 (The Pile)

Max Activating Token Index: 19

Text #1

Max Range: 3.8135. Min Range: -3.8135

Max Act: 3.7794. Min Act: -0.0000

Data Index: 1666440 (The Pile)

Max Activating Token Index: 886

Text #2

Max Range: 3.8135. Min Range: -3.8135

Max Act: 3.5730. Min Act: -0.0000

Data Index: 1191060 (The Pile)

Max Activating Token Index: 411

Text #3

Max Range: 3.8135. Min Range: -3.8135

Max Act: 3.4320. Min Act: -0.0000

Data Index: 646958 (The Pile)

Max Activating Token Index: 261

Text #4

Max Range: 3.8135. Min Range: -3.8135

Max Act: 3.4273. Min Act: -0.0000

Data Index: 1457038 (The Pile)

Max Activating Token Index: 16

Text #5

Max Range: 3.8135. Min Range: -3.8135

Max Act: 3.5645. Min Act: -0.0000

Data Index: 206239 (The Pile)

Max Activating Token Index: 333

Text #6

Max Range: 3.8135. Min Range: -3.8135

Max Act: 3.3993. Min Act: -0.0000

Data Index: 706951 (The Pile)

Max Activating Token Index: 627

Text #7

Max Range: 3.8135. Min Range: -3.8135

Max Act: 3.3632. Min Act: -0.0000

Data Index: 1244553 (The Pile)

Max Activating Token Index: 69

Text #8

Max Range: 3.8135. Min Range: -3.8135

Max Act: 3.4418. Min Act: -0.0000

Data Index: 1375614 (The Pile)

Max Activating Token Index: 369

Text #9

Max Range: 3.8135. Min Range: -3.8135

Max Act: 3.0167. Min Act: -0.0000

Data Index: 831749 (The Pile)

Max Activating Token Index: 26

Text #10

Max Range: 3.8135. Min Range: -3.8135

Max Act: 3.1559. Min Act: -0.0000

Data Index: 607051 (The Pile)

Max Activating Token Index: 192

Text #11

Max Range: 3.8135. Min Range: -3.8135

Max Act: 3.1274. Min Act: -0.0000

Data Index: 170520 (The Pile)

Max Activating Token Index: 118

Text #12

Max Range: 3.8135. Min Range: -3.8135

Max Act: 3.1186. Min Act: -0.0000

Data Index: 145059 (The Pile)

Max Activating Token Index: 346

Text #13

Max Range: 3.8135. Min Range: -3.8135

Max Act: 2.9779. Min Act: -0.0000

Data Index: 535519 (The Pile)

Max Activating Token Index: 477

Text #14

Max Range: 3.8135. Min Range: -3.8135

Max Act: 3.0842. Min Act: -0.0000

Data Index: 1154290 (The Pile)

Max Activating Token Index: 369

Text #15

Max Range: 3.8135. Min Range: -3.8135

Max Act: 2.8275. Min Act: -0.0000

Data Index: 952116 (The Pile)

Max Activating Token Index: 128

Text #16

Max Range: 3.8135. Min Range: -3.8135

Max Act: 3.0397. Min Act: -0.0000

Data Index: 435566 (The Pile)

Max Activating Token Index: 117

Text #17

Max Range: 3.8135. Min Range: -3.8135

Max Act: 3.1933. Min Act: -0.0000

Data Index: 74032 (The Pile)

Max Activating Token Index: 163

Text #18

Max Range: 3.8135. Min Range: -3.8135

Max Act: 3.0331. Min Act: -0.0000

Data Index: 1320827 (The Pile)

Max Activating Token Index: 385

Text #19

Max Range: 3.8135. Min Range: -3.8135

Max Act: 2.8994. Min Act: -0.0000

Data Index: 1170428 (The Pile)

Max Activating Token Index: 11