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

Dataset: The Pile

Neuron 1327 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6085. Min Range: -1.6085

Max Act: 1.6085. Min Act: -0.0000

Data Index: 1936388 (The Pile)

Max Activating Token Index: 761

Text #1

Max Range: 1.6085. Min Range: -1.6085

Max Act: 1.3521. Min Act: -0.0000

Data Index: 115481 (The Pile)

Max Activating Token Index: 665

Text #2

Max Range: 1.6085. Min Range: -1.6085

Max Act: 1.2907. Min Act: -0.0000

Data Index: 939529 (The Pile)

Max Activating Token Index: 941

Text #3

Max Range: 1.6085. Min Range: -1.6085

Max Act: 1.2194. Min Act: -0.0000

Data Index: 433656 (The Pile)

Max Activating Token Index: 662

Text #4

Max Range: 1.6085. Min Range: -1.6085

Max Act: 1.0066. Min Act: -0.0000

Data Index: 303903 (The Pile)

Max Activating Token Index: 895

Text #5

Max Range: 1.6085. Min Range: -1.6085

Max Act: 1.1862. Min Act: -0.0000

Data Index: 1917772 (The Pile)

Max Activating Token Index: 845

Text #6

Max Range: 1.6085. Min Range: -1.6085

Max Act: 1.0712. Min Act: -0.0000

Data Index: 291884 (The Pile)

Max Activating Token Index: 410

Text #7

Max Range: 1.6085. Min Range: -1.6085

Max Act: 1.1166. Min Act: -0.0000

Data Index: 1790492 (The Pile)

Max Activating Token Index: 258

Text #8

Max Range: 1.6085. Min Range: -1.6085

Max Act: 1.0620. Min Act: -0.0000

Data Index: 1248068 (The Pile)

Max Activating Token Index: 328

Text #9

Max Range: 1.6085. Min Range: -1.6085

Max Act: 1.1268. Min Act: -0.0000

Data Index: 1066555 (The Pile)

Max Activating Token Index: 426

Text #10

Max Range: 1.6085. Min Range: -1.6085

Max Act: 1.0680. Min Act: -0.0000

Data Index: 204075 (The Pile)

Max Activating Token Index: 667

Text #11

Max Range: 1.6085. Min Range: -1.6085

Max Act: 1.0792. Min Act: -0.0000

Data Index: 508523 (The Pile)

Max Activating Token Index: 681

Text #12

Max Range: 1.6085. Min Range: -1.6085

Max Act: 1.0506. Min Act: -0.0000

Data Index: 490609 (The Pile)

Max Activating Token Index: 650

Text #13

Max Range: 1.6085. Min Range: -1.6085

Max Act: 1.0599. Min Act: -0.0000

Data Index: 971130 (The Pile)

Max Activating Token Index: 806

Text #14

Max Range: 1.6085. Min Range: -1.6085

Max Act: 1.0753. Min Act: -0.0000

Data Index: 1079353 (The Pile)

Max Activating Token Index: 705

Text #15

Max Range: 1.6085. Min Range: -1.6085

Max Act: 0.9611. Min Act: -0.0000

Data Index: 1370321 (The Pile)

Max Activating Token Index: 93

Text #16

Max Range: 1.6085. Min Range: -1.6085

Max Act: 1.0204. Min Act: -0.0000

Data Index: 304860 (The Pile)

Max Activating Token Index: 674

Text #17

Max Range: 1.6085. Min Range: -1.6085

Max Act: 1.0105. Min Act: -0.0000

Data Index: 1667105 (The Pile)

Max Activating Token Index: 716

Text #18

Max Range: 1.6085. Min Range: -1.6085

Max Act: 0.9787. Min Act: -0.0000

Data Index: 944398 (The Pile)

Max Activating Token Index: 190

Text #19

Max Range: 1.6085. Min Range: -1.6085

Max Act: 0.9212. Min Act: -0.0000

Data Index: 274380 (The Pile)

Max Activating Token Index: 738