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

Dataset: The Pile

Neuron 164 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8690. Min Range: -1.8690

Max Act: 1.8690. Min Act: -0.0000

Data Index: 1188048 (The Pile)

Max Activating Token Index: 773

Text #1

Max Range: 1.8690. Min Range: -1.8690

Max Act: 1.6044. Min Act: -0.0000

Data Index: 1952505 (The Pile)

Max Activating Token Index: 418

Text #2

Max Range: 1.8690. Min Range: -1.8690

Max Act: 1.5064. Min Act: -0.0000

Data Index: 1478782 (The Pile)

Max Activating Token Index: 162

Text #3

Max Range: 1.8690. Min Range: -1.8690

Max Act: 1.4231. Min Act: -0.0000

Data Index: 1673718 (The Pile)

Max Activating Token Index: 331

Text #4

Max Range: 1.8690. Min Range: -1.8690

Max Act: 1.4243. Min Act: -0.0000

Data Index: 961522 (The Pile)

Max Activating Token Index: 519

Text #5

Max Range: 1.8690. Min Range: -1.8690

Max Act: 1.3440. Min Act: -0.0000

Data Index: 36048 (The Pile)

Max Activating Token Index: 174

Text #6

Max Range: 1.8690. Min Range: -1.8690

Max Act: 1.3193. Min Act: -0.0000

Data Index: 293151 (The Pile)

Max Activating Token Index: 552

Text #7

Max Range: 1.8690. Min Range: -1.8690

Max Act: 1.3664. Min Act: -0.0000

Data Index: 1258875 (The Pile)

Max Activating Token Index: 1012

Text #8

Max Range: 1.8690. Min Range: -1.8690

Max Act: 1.2839. Min Act: -0.0000

Data Index: 1133233 (The Pile)

Max Activating Token Index: 574

Text #9

Max Range: 1.8690. Min Range: -1.8690

Max Act: 1.3259. Min Act: -0.0000

Data Index: 907869 (The Pile)

Max Activating Token Index: 323

Text #10

Max Range: 1.8690. Min Range: -1.8690

Max Act: 1.3216. Min Act: -0.0000

Data Index: 1755325 (The Pile)

Max Activating Token Index: 375

Text #11

Max Range: 1.8690. Min Range: -1.8690

Max Act: 1.2473. Min Act: -0.0000

Data Index: 1459802 (The Pile)

Max Activating Token Index: 521

Text #12

Max Range: 1.8690. Min Range: -1.8690

Max Act: 1.2733. Min Act: -0.0000

Data Index: 1110149 (The Pile)

Max Activating Token Index: 357

Text #13

Max Range: 1.8690. Min Range: -1.8690

Max Act: 1.2444. Min Act: -0.0000

Data Index: 1232226 (The Pile)

Max Activating Token Index: 226

Text #14

Max Range: 1.8690. Min Range: -1.8690

Max Act: 1.3133. Min Act: -0.0000

Data Index: 1118950 (The Pile)

Max Activating Token Index: 1003

Text #15

Max Range: 1.8690. Min Range: -1.8690

Max Act: 1.1868. Min Act: -0.0000

Data Index: 80150 (The Pile)

Max Activating Token Index: 78

Text #16

Max Range: 1.8690. Min Range: -1.8690

Max Act: 1.2234. Min Act: -0.0000

Data Index: 1351084 (The Pile)

Max Activating Token Index: 923

Text #17

Max Range: 1.8690. Min Range: -1.8690

Max Act: 1.2596. Min Act: -0.0000

Data Index: 1586888 (The Pile)

Max Activating Token Index: 733

Text #18

Max Range: 1.8690. Min Range: -1.8690

Max Act: 1.3071. Min Act: -0.0000

Data Index: 153514 (The Pile)

Max Activating Token Index: 893

Text #19

Max Range: 1.8690. Min Range: -1.8690

Max Act: 1.2133. Min Act: -0.0000

Data Index: 1705146 (The Pile)

Max Activating Token Index: 475