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

Dataset: The Pile

Neuron 4628 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.7853. Min Act: -0.0000

Data Index: 1517010 (The Pile)

Max Activating Token Index: 582

Text #1

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.7808. Min Act: -0.0000

Data Index: 864318 (The Pile)

Max Activating Token Index: 489

Text #2

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.7215. Min Act: -0.0000

Data Index: 1305518 (The Pile)

Max Activating Token Index: 1015

Text #3

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.6473. Min Act: -0.0000

Data Index: 1609891 (The Pile)

Max Activating Token Index: 1005

Text #4

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.7195. Min Act: -0.0000

Data Index: 183550 (The Pile)

Max Activating Token Index: 312

Text #5

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.7293. Min Act: -0.0000

Data Index: 1971175 (The Pile)

Max Activating Token Index: 181

Text #6

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.7267. Min Act: -0.0000

Data Index: 504221 (The Pile)

Max Activating Token Index: 716

Text #7

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.7094. Min Act: -0.0000

Data Index: 1815213 (The Pile)

Max Activating Token Index: 545

Text #8

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.6759. Min Act: -0.0000

Data Index: 1386597 (The Pile)

Max Activating Token Index: 888

Text #9

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.6615. Min Act: -0.0000

Data Index: 202919 (The Pile)

Max Activating Token Index: 142

Text #10

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.6106. Min Act: -0.0000

Data Index: 1685498 (The Pile)

Max Activating Token Index: 718

Text #11

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.6423. Min Act: -0.0000

Data Index: 92177 (The Pile)

Max Activating Token Index: 231

Text #12

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.6389. Min Act: -0.0000

Data Index: 1022461 (The Pile)

Max Activating Token Index: 172

Text #13

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.6231. Min Act: -0.0000

Data Index: 211199 (The Pile)

Max Activating Token Index: 415

Text #14

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.6350. Min Act: -0.0000

Data Index: 1253826 (The Pile)

Max Activating Token Index: 501

Text #15

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.5765. Min Act: -0.0000

Data Index: 868723 (The Pile)

Max Activating Token Index: 239

Text #16

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.6113. Min Act: -0.0000

Data Index: 267736 (The Pile)

Max Activating Token Index: 658

Text #17

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.5815. Min Act: -0.0000

Data Index: 490646 (The Pile)

Max Activating Token Index: 704

Text #18

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.5869. Min Act: -0.0000

Data Index: 1494924 (The Pile)

Max Activating Token Index: 385

Text #19

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.5411. Min Act: -0.0000

Data Index: 1174084 (The Pile)

Max Activating Token Index: 199