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

Dataset: The Pile

Neuron 3517 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: 1.1334. Min Range: -1.1334

Max Act: 1.1334. Min Act: -0.0000

Data Index: 1602939 (The Pile)

Max Activating Token Index: 539

Text #1

Max Range: 1.1334. Min Range: -1.1334

Max Act: 0.9936. Min Act: -0.0000

Data Index: 1433082 (The Pile)

Max Activating Token Index: 297

Text #2

Max Range: 1.1334. Min Range: -1.1334

Max Act: 0.9163. Min Act: -0.0000

Data Index: 1377852 (The Pile)

Max Activating Token Index: 501

Text #3

Max Range: 1.1334. Min Range: -1.1334

Max Act: 0.8522. Min Act: -0.0000

Data Index: 779683 (The Pile)

Max Activating Token Index: 858

Text #4

Max Range: 1.1334. Min Range: -1.1334

Max Act: 0.8653. Min Act: -0.0000

Data Index: 610004 (The Pile)

Max Activating Token Index: 228

Text #5

Max Range: 1.1334. Min Range: -1.1334

Max Act: 0.7843. Min Act: -0.0000

Data Index: 622195 (The Pile)

Max Activating Token Index: 717

Text #6

Max Range: 1.1334. Min Range: -1.1334

Max Act: 0.7989. Min Act: -0.0000

Data Index: 1497899 (The Pile)

Max Activating Token Index: 266

Text #7

Max Range: 1.1334. Min Range: -1.1334

Max Act: 0.8474. Min Act: -0.0000

Data Index: 1029061 (The Pile)

Max Activating Token Index: 273

Text #8

Max Range: 1.1334. Min Range: -1.1334

Max Act: 0.8197. Min Act: -0.0000

Data Index: 674140 (The Pile)

Max Activating Token Index: 270

Text #9

Max Range: 1.1334. Min Range: -1.1334

Max Act: 0.8408. Min Act: -0.0000

Data Index: 793926 (The Pile)

Max Activating Token Index: 108

Text #10

Max Range: 1.1334. Min Range: -1.1334

Max Act: 0.7911. Min Act: -0.0000

Data Index: 977747 (The Pile)

Max Activating Token Index: 412

Text #11

Max Range: 1.1334. Min Range: -1.1334

Max Act: 0.7699. Min Act: -0.0000

Data Index: 1222729 (The Pile)

Max Activating Token Index: 879

Text #12

Max Range: 1.1334. Min Range: -1.1334

Max Act: 0.7343. Min Act: -0.0000

Data Index: 453840 (The Pile)

Max Activating Token Index: 279

Text #13

Max Range: 1.1334. Min Range: -1.1334

Max Act: 0.7607. Min Act: -0.0000

Data Index: 209987 (The Pile)

Max Activating Token Index: 649

Text #14

Max Range: 1.1334. Min Range: -1.1334

Max Act: 0.7977. Min Act: -0.0000

Data Index: 10441 (The Pile)

Max Activating Token Index: 890

Text #15

Max Range: 1.1334. Min Range: -1.1334

Max Act: 0.6974. Min Act: -0.0000

Data Index: 1109710 (The Pile)

Max Activating Token Index: 86

Text #16

Max Range: 1.1334. Min Range: -1.1334

Max Act: 0.7620. Min Act: -0.0000

Data Index: 323031 (The Pile)

Max Activating Token Index: 750

Text #17

Max Range: 1.1334. Min Range: -1.1334

Max Act: 0.8039. Min Act: -0.0000

Data Index: 1593946 (The Pile)

Max Activating Token Index: 112

Text #18

Max Range: 1.1334. Min Range: -1.1334

Max Act: 0.8017. Min Act: -0.0000

Data Index: 261371 (The Pile)

Max Activating Token Index: 489

Text #19

Max Range: 1.1334. Min Range: -1.1334

Max Act: 0.7775. Min Act: -0.0000

Data Index: 1672282 (The Pile)

Max Activating Token Index: 373