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

Dataset: The Pile

Neuron 3292 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: 1.7323. Min Range: -1.7323

Max Act: 1.7323. Min Act: -0.0000

Data Index: 268169 (The Pile)

Max Activating Token Index: 323

Text #1

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.5065. Min Act: -0.0000

Data Index: 1452092 (The Pile)

Max Activating Token Index: 315

Text #2

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.6362. Min Act: -0.0000

Data Index: 1709415 (The Pile)

Max Activating Token Index: 362

Text #3

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.1647. Min Act: -0.0000

Data Index: 1270420 (The Pile)

Max Activating Token Index: 928

Text #4

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.4022. Min Act: -0.0000

Data Index: 1626258 (The Pile)

Max Activating Token Index: 956

Text #5

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.4352. Min Act: -0.0000

Data Index: 1142129 (The Pile)

Max Activating Token Index: 6

Text #6

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.4161. Min Act: -0.0000

Data Index: 1592811 (The Pile)

Max Activating Token Index: 43

Text #7

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.2708. Min Act: -0.0000

Data Index: 1510164 (The Pile)

Max Activating Token Index: 480

Text #8

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.3045. Min Act: -0.0000

Data Index: 1739573 (The Pile)

Max Activating Token Index: 1012

Text #9

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.2433. Min Act: -0.0000

Data Index: 935850 (The Pile)

Max Activating Token Index: 453

Text #10

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.1153. Min Act: -0.0000

Data Index: 1106479 (The Pile)

Max Activating Token Index: 983

Text #11

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.2181. Min Act: -0.0000

Data Index: 418440 (The Pile)

Max Activating Token Index: 866

Text #12

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.1835. Min Act: -0.0000

Data Index: 1234954 (The Pile)

Max Activating Token Index: 704

Text #13

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.2097. Min Act: -0.0000

Data Index: 454183 (The Pile)

Max Activating Token Index: 972

Text #14

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.2688. Min Act: -0.0000

Data Index: 391122 (The Pile)

Max Activating Token Index: 727

Text #15

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.1928. Min Act: -0.0000

Data Index: 193405 (The Pile)

Max Activating Token Index: 14

Text #16

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.0602. Min Act: -0.0000

Data Index: 765172 (The Pile)

Max Activating Token Index: 138

Text #17

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.1263. Min Act: -0.0000

Data Index: 115397 (The Pile)

Max Activating Token Index: 286

Text #18

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.1441. Min Act: -0.0000

Data Index: 779330 (The Pile)

Max Activating Token Index: 4

Text #19

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.1441. Min Act: -0.0000

Data Index: 1206717 (The Pile)

Max Activating Token Index: 4