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

Dataset: The Pile

Neuron 3883 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 11.9074. Min Range: -11.9074

Max Act: 11.6445. Min Act: -0.0000

Data Index: 328134 (The Pile)

Max Activating Token Index: 204

Text #1

Max Range: 11.9074. Min Range: -11.9074

Max Act: 11.1864. Min Act: -0.0000

Data Index: 297106 (The Pile)

Max Activating Token Index: 69

Text #2

Max Range: 11.9074. Min Range: -11.9074

Max Act: 11.3238. Min Act: -0.0000

Data Index: 221037 (The Pile)

Max Activating Token Index: 204

Text #3

Max Range: 11.9074. Min Range: -11.9074

Max Act: 11.5509. Min Act: -0.0000

Data Index: 354479 (The Pile)

Max Activating Token Index: 236

Text #4

Max Range: 11.9074. Min Range: -11.9074

Max Act: 11.9074. Min Act: -0.0000

Data Index: 1401710 (The Pile)

Max Activating Token Index: 237

Text #5

Max Range: 11.9074. Min Range: -11.9074

Max Act: 11.1888. Min Act: -0.0000

Data Index: 1097446 (The Pile)

Max Activating Token Index: 674

Text #6

Max Range: 11.9074. Min Range: -11.9074

Max Act: 11.7238. Min Act: -0.0000

Data Index: 1628860 (The Pile)

Max Activating Token Index: 120

Text #7

Max Range: 11.9074. Min Range: -11.9074

Max Act: 11.7215. Min Act: -0.0000

Data Index: 1280630 (The Pile)

Max Activating Token Index: 203

Text #8

Max Range: 11.9074. Min Range: -11.9074

Max Act: 11.6234. Min Act: -0.0000

Data Index: 210536 (The Pile)

Max Activating Token Index: 264

Text #9

Max Range: 11.9074. Min Range: -11.9074

Max Act: 11.4651. Min Act: -0.0000

Data Index: 688499 (The Pile)

Max Activating Token Index: 206

Text #10

Max Range: 11.9074. Min Range: -11.9074

Max Act: 11.9033. Min Act: -0.0000

Data Index: 1835926 (The Pile)

Max Activating Token Index: 419

Text #11

Max Range: 11.9074. Min Range: -11.9074

Max Act: 11.6518. Min Act: -0.0000

Data Index: 1461315 (The Pile)

Max Activating Token Index: 198

Text #12

Max Range: 11.9074. Min Range: -11.9074

Max Act: 11.5774. Min Act: -0.0000

Data Index: 416998 (The Pile)

Max Activating Token Index: 36

Text #13

Max Range: 11.9074. Min Range: -11.9074

Max Act: 11.1890. Min Act: -0.0000

Data Index: 1800671 (The Pile)

Max Activating Token Index: 376

Text #14

Max Range: 11.9074. Min Range: -11.9074

Max Act: 11.2348. Min Act: -0.0000

Data Index: 891598 (The Pile)

Max Activating Token Index: 237

Text #15

Max Range: 11.9074. Min Range: -11.9074

Max Act: 11.0068. Min Act: -0.0000

Data Index: 86126 (The Pile)

Max Activating Token Index: 309

Text #16

Max Range: 11.9074. Min Range: -11.9074

Max Act: 10.9664. Min Act: -0.0000

Data Index: 1362449 (The Pile)

Max Activating Token Index: 484

Text #17

Max Range: 11.9074. Min Range: -11.9074

Max Act: 11.4566. Min Act: -0.0000

Data Index: 1672268 (The Pile)

Max Activating Token Index: 156

Text #18

Max Range: 11.9074. Min Range: -11.9074

Max Act: 11.8075. Min Act: -0.0000

Data Index: 789370 (The Pile)

Max Activating Token Index: 307

Text #19

Max Range: 11.9074. Min Range: -11.9074

Max Act: 10.6397. Min Act: -0.0000

Data Index: 271717 (The Pile)

Max Activating Token Index: 641