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

Dataset: The Pile

Neuron 1059 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5216. Min Range: -3.5216

Max Act: 3.5216. Min Act: -0.0000

Data Index: 1811281 (The Pile)

Max Activating Token Index: 133

Text #1

Max Range: 3.5216. Min Range: -3.5216

Max Act: 3.4778. Min Act: -0.0000

Data Index: 394688 (The Pile)

Max Activating Token Index: 175

Text #2

Max Range: 3.5216. Min Range: -3.5216

Max Act: 3.3031. Min Act: -0.0000

Data Index: 1930573 (The Pile)

Max Activating Token Index: 366

Text #3

Max Range: 3.5216. Min Range: -3.5216

Max Act: 2.8576. Min Act: -0.0000

Data Index: 176524 (The Pile)

Max Activating Token Index: 272

Text #4

Max Range: 3.5216. Min Range: -3.5216

Max Act: 3.2088. Min Act: -0.0000

Data Index: 451560 (The Pile)

Max Activating Token Index: 514

Text #5

Max Range: 3.5216. Min Range: -3.5216

Max Act: 3.2863. Min Act: -0.0000

Data Index: 772892 (The Pile)

Max Activating Token Index: 405

Text #6

Max Range: 3.5216. Min Range: -3.5216

Max Act: 3.2120. Min Act: -0.0000

Data Index: 758738 (The Pile)

Max Activating Token Index: 393

Text #7

Max Range: 3.5216. Min Range: -3.5216

Max Act: 3.2085. Min Act: -0.0000

Data Index: 1246846 (The Pile)

Max Activating Token Index: 284

Text #8

Max Range: 3.5216. Min Range: -3.5216

Max Act: 3.0363. Min Act: -0.0000

Data Index: 1191269 (The Pile)

Max Activating Token Index: 83

Text #9

Max Range: 3.5216. Min Range: -3.5216

Max Act: 3.0083. Min Act: -0.0000

Data Index: 1998042 (The Pile)

Max Activating Token Index: 869

Text #10

Max Range: 3.5216. Min Range: -3.5216

Max Act: 3.4992. Min Act: -0.0000

Data Index: 1272398 (The Pile)

Max Activating Token Index: 117

Text #11

Max Range: 3.5216. Min Range: -3.5216

Max Act: 3.1350. Min Act: -0.0000

Data Index: 1673998 (The Pile)

Max Activating Token Index: 699

Text #12

Max Range: 3.5216. Min Range: -3.5216

Max Act: 3.0035. Min Act: -0.0000

Data Index: 1879207 (The Pile)

Max Activating Token Index: 278

Text #13

Max Range: 3.5216. Min Range: -3.5216

Max Act: 3.1544. Min Act: -0.0000

Data Index: 420057 (The Pile)

Max Activating Token Index: 741

Text #14

Max Range: 3.5216. Min Range: -3.5216

Max Act: 2.9439. Min Act: -0.0000

Data Index: 57532 (The Pile)

Max Activating Token Index: 118

Text #15

Max Range: 3.5216. Min Range: -3.5216

Max Act: 3.0334. Min Act: -0.0000

Data Index: 806672 (The Pile)

Max Activating Token Index: 385

Text #16

Max Range: 3.5216. Min Range: -3.5216

Max Act: 3.0837. Min Act: -0.0000

Data Index: 105232 (The Pile)

Max Activating Token Index: 258

Text #17

Max Range: 3.5216. Min Range: -3.5216

Max Act: 3.0578. Min Act: -0.0000

Data Index: 1750326 (The Pile)

Max Activating Token Index: 338

Text #18

Max Range: 3.5216. Min Range: -3.5216

Max Act: 3.0438. Min Act: -0.0000

Data Index: 1725527 (The Pile)

Max Activating Token Index: 469

Text #19

Max Range: 3.5216. Min Range: -3.5216

Max Act: 2.9138. Min Act: -0.0000

Data Index: 137163 (The Pile)

Max Activating Token Index: 421