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

Dataset: The Pile

Neuron 3676 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.3804. Min Act: -0.0000

Data Index: 1545996 (The Pile)

Max Activating Token Index: 297

Text #1

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.3719. Min Act: -0.0000

Data Index: 1589339 (The Pile)

Max Activating Token Index: 225

Text #2

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.3559. Min Act: -0.0000

Data Index: 492564 (The Pile)

Max Activating Token Index: 181

Text #3

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.3190. Min Act: -0.0000

Data Index: 1907219 (The Pile)

Max Activating Token Index: 410

Text #4

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.3003. Min Act: -0.0000

Data Index: 632503 (The Pile)

Max Activating Token Index: 563

Text #5

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.3542. Min Act: -0.0000

Data Index: 300779 (The Pile)

Max Activating Token Index: 335

Text #6

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.3316. Min Act: -0.0000

Data Index: 1230936 (The Pile)

Max Activating Token Index: 336

Text #7

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.2940. Min Act: -0.0000

Data Index: 93097 (The Pile)

Max Activating Token Index: 423

Text #8

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.2477. Min Act: -0.0000

Data Index: 1492344 (The Pile)

Max Activating Token Index: 205

Text #9

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.2662. Min Act: -0.0000

Data Index: 797682 (The Pile)

Max Activating Token Index: 284

Text #10

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.2465. Min Act: -0.0000

Data Index: 474516 (The Pile)

Max Activating Token Index: 825

Text #11

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.2532. Min Act: -0.0000

Data Index: 1105787 (The Pile)

Max Activating Token Index: 724

Text #12

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.2920. Min Act: -0.0000

Data Index: 513220 (The Pile)

Max Activating Token Index: 213

Text #13

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.2630. Min Act: -0.0000

Data Index: 1063338 (The Pile)

Max Activating Token Index: 293

Text #14

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.2327. Min Act: -0.0000

Data Index: 1562669 (The Pile)

Max Activating Token Index: 369

Text #15

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.2303. Min Act: -0.0000

Data Index: 1018822 (The Pile)

Max Activating Token Index: 176

Text #16

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.2282. Min Act: -0.0000

Data Index: 1725897 (The Pile)

Max Activating Token Index: 350

Text #17

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.1836. Min Act: -0.0000

Data Index: 743950 (The Pile)

Max Activating Token Index: 581

Text #18

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.2166. Min Act: -0.0000

Data Index: 455958 (The Pile)

Max Activating Token Index: 160

Text #19

Max Range: 0.3804. Min Range: -0.3804

Max Act: 0.2202. Min Act: -0.0000

Data Index: 1737777 (The Pile)

Max Activating Token Index: 525