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

Dataset: The Pile

Neuron 2393 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: 1.3188. Min Range: -1.3188

Max Act: 1.3188. Min Act: -0.0000

Data Index: 1442837 (The Pile)

Max Activating Token Index: 393

Text #1

Max Range: 1.3188. Min Range: -1.3188

Max Act: 1.1450. Min Act: -0.0000

Data Index: 1960495 (The Pile)

Max Activating Token Index: 272

Text #2

Max Range: 1.3188. Min Range: -1.3188

Max Act: 1.1398. Min Act: -0.0000

Data Index: 1025643 (The Pile)

Max Activating Token Index: 110

Text #3

Max Range: 1.3188. Min Range: -1.3188

Max Act: 1.0183. Min Act: -0.0000

Data Index: 1636783 (The Pile)

Max Activating Token Index: 547

Text #4

Max Range: 1.3188. Min Range: -1.3188

Max Act: 1.1750. Min Act: -0.0000

Data Index: 1443524 (The Pile)

Max Activating Token Index: 134

Text #5

Max Range: 1.3188. Min Range: -1.3188

Max Act: 1.1044. Min Act: -0.0000

Data Index: 1273019 (The Pile)

Max Activating Token Index: 1014

Text #6

Max Range: 1.3188. Min Range: -1.3188

Max Act: 1.1250. Min Act: -0.0000

Data Index: 1692429 (The Pile)

Max Activating Token Index: 202

Text #7

Max Range: 1.3188. Min Range: -1.3188

Max Act: 0.9920. Min Act: -0.0000

Data Index: 1192414 (The Pile)

Max Activating Token Index: 349

Text #8

Max Range: 1.3188. Min Range: -1.3188

Max Act: 0.8744. Min Act: -0.0000

Data Index: 735869 (The Pile)

Max Activating Token Index: 812

Text #9

Max Range: 1.3188. Min Range: -1.3188

Max Act: 1.0176. Min Act: -0.0000

Data Index: 1245988 (The Pile)

Max Activating Token Index: 306

Text #10

Max Range: 1.3188. Min Range: -1.3188

Max Act: 1.0381. Min Act: -0.0000

Data Index: 666584 (The Pile)

Max Activating Token Index: 307

Text #11

Max Range: 1.3188. Min Range: -1.3188

Max Act: 1.0627. Min Act: -0.0000

Data Index: 207787 (The Pile)

Max Activating Token Index: 24

Text #12

Max Range: 1.3188. Min Range: -1.3188

Max Act: 1.0562. Min Act: -0.0000

Data Index: 555691 (The Pile)

Max Activating Token Index: 93

Text #13

Max Range: 1.3188. Min Range: -1.3188

Max Act: 1.0216. Min Act: -0.0000

Data Index: 455407 (The Pile)

Max Activating Token Index: 372

Text #14

Max Range: 1.3188. Min Range: -1.3188

Max Act: 0.9770. Min Act: -0.0000

Data Index: 244833 (The Pile)

Max Activating Token Index: 191

Text #15

Max Range: 1.3188. Min Range: -1.3188

Max Act: 0.9684. Min Act: -0.0000

Data Index: 526592 (The Pile)

Max Activating Token Index: 318

Text #16

Max Range: 1.3188. Min Range: -1.3188

Max Act: 0.9094. Min Act: -0.0000

Data Index: 1720469 (The Pile)

Max Activating Token Index: 366

Text #17

Max Range: 1.3188. Min Range: -1.3188

Max Act: 0.9872. Min Act: -0.0000

Data Index: 1504161 (The Pile)

Max Activating Token Index: 115

Text #18

Max Range: 1.3188. Min Range: -1.3188

Max Act: 1.0154. Min Act: -0.0000

Data Index: 893308 (The Pile)

Max Activating Token Index: 879

Text #19

Max Range: 1.3188. Min Range: -1.3188

Max Act: 0.9622. Min Act: -0.0000

Data Index: 675096 (The Pile)

Max Activating Token Index: 304