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

Dataset: The Pile

Neuron 2842 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: 1.2864. Min Range: -1.2864

Max Act: 1.2864. Min Act: -0.0000

Data Index: 1789320 (The Pile)

Max Activating Token Index: 797

Text #1

Max Range: 1.2864. Min Range: -1.2864

Max Act: 1.1682. Min Act: -0.0000

Data Index: 315178 (The Pile)

Max Activating Token Index: 472

Text #2

Max Range: 1.2864. Min Range: -1.2864

Max Act: 1.1542. Min Act: -0.0000

Data Index: 548566 (The Pile)

Max Activating Token Index: 425

Text #3

Max Range: 1.2864. Min Range: -1.2864

Max Act: 1.0769. Min Act: -0.0000

Data Index: 671062 (The Pile)

Max Activating Token Index: 740

Text #4

Max Range: 1.2864. Min Range: -1.2864

Max Act: 1.0037. Min Act: -0.0000

Data Index: 528631 (The Pile)

Max Activating Token Index: 338

Text #5

Max Range: 1.2864. Min Range: -1.2864

Max Act: 0.9421. Min Act: -0.0000

Data Index: 890177 (The Pile)

Max Activating Token Index: 409

Text #6

Max Range: 1.2864. Min Range: -1.2864

Max Act: 0.9000. Min Act: -0.0000

Data Index: 1682032 (The Pile)

Max Activating Token Index: 222

Text #7

Max Range: 1.2864. Min Range: -1.2864

Max Act: 0.9191. Min Act: -0.0000

Data Index: 1183095 (The Pile)

Max Activating Token Index: 508

Text #8

Max Range: 1.2864. Min Range: -1.2864

Max Act: 0.8638. Min Act: -0.0000

Data Index: 167763 (The Pile)

Max Activating Token Index: 356

Text #9

Max Range: 1.2864. Min Range: -1.2864

Max Act: 0.8417. Min Act: -0.0000

Data Index: 1696277 (The Pile)

Max Activating Token Index: 152

Text #10

Max Range: 1.2864. Min Range: -1.2864

Max Act: 0.7765. Min Act: -0.0000

Data Index: 1670656 (The Pile)

Max Activating Token Index: 280

Text #11

Max Range: 1.2864. Min Range: -1.2864

Max Act: 0.7443. Min Act: -0.0000

Data Index: 508087 (The Pile)

Max Activating Token Index: 924

Text #12

Max Range: 1.2864. Min Range: -1.2864

Max Act: 0.7857. Min Act: -0.0000

Data Index: 1882600 (The Pile)

Max Activating Token Index: 529

Text #13

Max Range: 1.2864. Min Range: -1.2864

Max Act: 0.7684. Min Act: -0.0000

Data Index: 19329 (The Pile)

Max Activating Token Index: 723

Text #14

Max Range: 1.2864. Min Range: -1.2864

Max Act: 0.7567. Min Act: -0.0000

Data Index: 1884568 (The Pile)

Max Activating Token Index: 334

Text #15

Max Range: 1.2864. Min Range: -1.2864

Max Act: 0.6806. Min Act: -0.0000

Data Index: 223475 (The Pile)

Max Activating Token Index: 193

Text #16

Max Range: 1.2864. Min Range: -1.2864

Max Act: 0.6559. Min Act: -0.0000

Data Index: 1115299 (The Pile)

Max Activating Token Index: 163

Text #17

Max Range: 1.2864. Min Range: -1.2864

Max Act: 0.5906. Min Act: -0.0000

Data Index: 1682560 (The Pile)

Max Activating Token Index: 833

Text #18

Max Range: 1.2864. Min Range: -1.2864

Max Act: 0.5699. Min Act: -0.0000

Data Index: 1317645 (The Pile)

Max Activating Token Index: 491

Text #19

Max Range: 1.2864. Min Range: -1.2864

Max Act: 0.5200. Min Act: -0.0000

Data Index: 911708 (The Pile)

Max Activating Token Index: 881