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

Dataset: The Pile

Neuron 3153 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: 0.4542. Min Range: -0.4542

Max Act: 0.4500. Min Act: -0.0000

Data Index: 1989714 (The Pile)

Max Activating Token Index: 539

Text #1

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.4237. Min Act: -0.0000

Data Index: 444244 (The Pile)

Max Activating Token Index: 176

Text #2

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.4542. Min Act: -0.0000

Data Index: 269814 (The Pile)

Max Activating Token Index: 385

Text #3

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.4360. Min Act: -0.0000

Data Index: 1437193 (The Pile)

Max Activating Token Index: 736

Text #4

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.4332. Min Act: -0.0000

Data Index: 1876189 (The Pile)

Max Activating Token Index: 523

Text #5

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.4152. Min Act: -0.0000

Data Index: 865793 (The Pile)

Max Activating Token Index: 609

Text #6

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.3476. Min Act: -0.0000

Data Index: 733614 (The Pile)

Max Activating Token Index: 832

Text #7

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.4141. Min Act: -0.0000

Data Index: 1574493 (The Pile)

Max Activating Token Index: 734

Text #8

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.3926. Min Act: -0.0000

Data Index: 1166984 (The Pile)

Max Activating Token Index: 673

Text #9

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.3965. Min Act: -0.0000

Data Index: 1580994 (The Pile)

Max Activating Token Index: 722

Text #10

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.3918. Min Act: -0.0000

Data Index: 1899703 (The Pile)

Max Activating Token Index: 425

Text #11

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.4001. Min Act: -0.0000

Data Index: 1718064 (The Pile)

Max Activating Token Index: 124

Text #12

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.3291. Min Act: -0.0000

Data Index: 1123832 (The Pile)

Max Activating Token Index: 959

Text #13

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.3351. Min Act: -0.0000

Data Index: 1559580 (The Pile)

Max Activating Token Index: 607

Text #14

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.3334. Min Act: -0.0000

Data Index: 217220 (The Pile)

Max Activating Token Index: 203

Text #15

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.3212. Min Act: -0.0000

Data Index: 180342 (The Pile)

Max Activating Token Index: 407

Text #16

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.3527. Min Act: -0.0000

Data Index: 458474 (The Pile)

Max Activating Token Index: 223

Text #17

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.3227. Min Act: -0.0000

Data Index: 1829672 (The Pile)

Max Activating Token Index: 687

Text #18

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.3659. Min Act: -0.0000

Data Index: 1104807 (The Pile)

Max Activating Token Index: 220

Text #19

Max Range: 0.4542. Min Range: -0.4542

Max Act: 0.3091. Min Act: -0.0000

Data Index: 290607 (The Pile)

Max Activating Token Index: 227