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

Dataset: The Pile

Neuron 4609 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: 0.9573. Min Range: -0.9573

Max Act: 0.9573. Min Act: -0.0000

Data Index: 426357 (The Pile)

Max Activating Token Index: 308

Text #1

Max Range: 0.9573. Min Range: -0.9573

Max Act: 0.9037. Min Act: -0.0000

Data Index: 1912623 (The Pile)

Max Activating Token Index: 569

Text #2

Max Range: 0.9573. Min Range: -0.9573

Max Act: 0.9153. Min Act: -0.0000

Data Index: 1766329 (The Pile)

Max Activating Token Index: 322

Text #3

Max Range: 0.9573. Min Range: -0.9573

Max Act: 0.9065. Min Act: -0.0000

Data Index: 580337 (The Pile)

Max Activating Token Index: 138

Text #4

Max Range: 0.9573. Min Range: -0.9573

Max Act: 0.8450. Min Act: -0.0000

Data Index: 139443 (The Pile)

Max Activating Token Index: 293

Text #5

Max Range: 0.9573. Min Range: -0.9573

Max Act: 0.8036. Min Act: -0.0000

Data Index: 1667676 (The Pile)

Max Activating Token Index: 224

Text #6

Max Range: 0.9573. Min Range: -0.9573

Max Act: 0.8276. Min Act: -0.0000

Data Index: 967232 (The Pile)

Max Activating Token Index: 95

Text #7

Max Range: 0.9573. Min Range: -0.9573

Max Act: 0.8031. Min Act: -0.0000

Data Index: 1683920 (The Pile)

Max Activating Token Index: 207

Text #8

Max Range: 0.9573. Min Range: -0.9573

Max Act: 0.7752. Min Act: -0.0000

Data Index: 53650 (The Pile)

Max Activating Token Index: 787

Text #9

Max Range: 0.9573. Min Range: -0.9573

Max Act: 0.6672. Min Act: -0.0000

Data Index: 1704022 (The Pile)

Max Activating Token Index: 918

Text #10

Max Range: 0.9573. Min Range: -0.9573

Max Act: 0.7650. Min Act: -0.0000

Data Index: 1652003 (The Pile)

Max Activating Token Index: 814

Text #11

Max Range: 0.9573. Min Range: -0.9573

Max Act: 0.7204. Min Act: -0.0000

Data Index: 1485917 (The Pile)

Max Activating Token Index: 128

Text #12

Max Range: 0.9573. Min Range: -0.9573

Max Act: 0.7111. Min Act: -0.0000

Data Index: 787451 (The Pile)

Max Activating Token Index: 167

Text #13

Max Range: 0.9573. Min Range: -0.9573

Max Act: 0.7547. Min Act: -0.0000

Data Index: 441582 (The Pile)

Max Activating Token Index: 306

Text #14

Max Range: 0.9573. Min Range: -0.9573

Max Act: 0.6456. Min Act: -0.0000

Data Index: 1435246 (The Pile)

Max Activating Token Index: 176

Text #15

Max Range: 0.9573. Min Range: -0.9573

Max Act: 0.7278. Min Act: -0.0000

Data Index: 1147081 (The Pile)

Max Activating Token Index: 548

Text #16

Max Range: 0.9573. Min Range: -0.9573

Max Act: 0.6728. Min Act: -0.0000

Data Index: 1267471 (The Pile)

Max Activating Token Index: 482

Text #17

Max Range: 0.9573. Min Range: -0.9573

Max Act: 0.7219. Min Act: -0.0000

Data Index: 211118 (The Pile)

Max Activating Token Index: 38

Text #18

Max Range: 0.9573. Min Range: -0.9573

Max Act: 0.7020. Min Act: -0.0000

Data Index: 1155113 (The Pile)

Max Activating Token Index: 709

Text #19

Max Range: 0.9573. Min Range: -0.9573

Max Act: 0.6441. Min Act: -0.0000

Data Index: 1851419 (The Pile)

Max Activating Token Index: 260