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

Dataset: The Pile

Neuron 3054 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: 1.7226. Min Range: -1.7226

Max Act: 1.7226. Min Act: -0.0000

Data Index: 1781080 (The Pile)

Max Activating Token Index: 952

Text #1

Max Range: 1.7226. Min Range: -1.7226

Max Act: 1.5064. Min Act: -0.0000

Data Index: 1400559 (The Pile)

Max Activating Token Index: 754

Text #2

Max Range: 1.7226. Min Range: -1.7226

Max Act: 1.3643. Min Act: -0.0000

Data Index: 325907 (The Pile)

Max Activating Token Index: 306

Text #3

Max Range: 1.7226. Min Range: -1.7226

Max Act: 1.3417. Min Act: -0.0000

Data Index: 1608324 (The Pile)

Max Activating Token Index: 667

Text #4

Max Range: 1.7226. Min Range: -1.7226

Max Act: 1.5323. Min Act: -0.0000

Data Index: 724266 (The Pile)

Max Activating Token Index: 97

Text #5

Max Range: 1.7226. Min Range: -1.7226

Max Act: 1.2836. Min Act: -0.0000

Data Index: 806310 (The Pile)

Max Activating Token Index: 421

Text #6

Max Range: 1.7226. Min Range: -1.7226

Max Act: 1.2262. Min Act: -0.0000

Data Index: 1552449 (The Pile)

Max Activating Token Index: 690

Text #7

Max Range: 1.7226. Min Range: -1.7226

Max Act: 1.0942. Min Act: -0.0000

Data Index: 842939 (The Pile)

Max Activating Token Index: 583

Text #8

Max Range: 1.7226. Min Range: -1.7226

Max Act: 1.1434. Min Act: -0.0000

Data Index: 1040416 (The Pile)

Max Activating Token Index: 406

Text #9

Max Range: 1.7226. Min Range: -1.7226

Max Act: 1.0800. Min Act: -0.0000

Data Index: 1824640 (The Pile)

Max Activating Token Index: 662

Text #10

Max Range: 1.7226. Min Range: -1.7226

Max Act: 1.0075. Min Act: -0.0000

Data Index: 137623 (The Pile)

Max Activating Token Index: 810

Text #11

Max Range: 1.7226. Min Range: -1.7226

Max Act: 1.0602. Min Act: -0.0000

Data Index: 1561325 (The Pile)

Max Activating Token Index: 158

Text #12

Max Range: 1.7226. Min Range: -1.7226

Max Act: 0.9371. Min Act: -0.0000

Data Index: 36435 (The Pile)

Max Activating Token Index: 928

Text #13

Max Range: 1.7226. Min Range: -1.7226

Max Act: 1.0878. Min Act: -0.0000

Data Index: 1273250 (The Pile)

Max Activating Token Index: 531

Text #14

Max Range: 1.7226. Min Range: -1.7226

Max Act: 0.9936. Min Act: -0.0000

Data Index: 1428204 (The Pile)

Max Activating Token Index: 801

Text #15

Max Range: 1.7226. Min Range: -1.7226

Max Act: 1.0283. Min Act: -0.0000

Data Index: 1532178 (The Pile)

Max Activating Token Index: 133

Text #16

Max Range: 1.7226. Min Range: -1.7226

Max Act: 1.0152. Min Act: -0.0000

Data Index: 1817884 (The Pile)

Max Activating Token Index: 538

Text #17

Max Range: 1.7226. Min Range: -1.7226

Max Act: 0.9557. Min Act: -0.0000

Data Index: 1479019 (The Pile)

Max Activating Token Index: 820

Text #18

Max Range: 1.7226. Min Range: -1.7226

Max Act: 1.0572. Min Act: -0.0000

Data Index: 1869887 (The Pile)

Max Activating Token Index: 378

Text #19

Max Range: 1.7226. Min Range: -1.7226

Max Act: 0.9094. Min Act: -0.0000

Data Index: 1383599 (The Pile)

Max Activating Token Index: 560