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

Dataset: The Pile

Neuron 3918 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: 5.6227. Min Range: -5.6227

Max Act: 5.6227. Min Act: -0.0000

Data Index: 130559 (The Pile)

Max Activating Token Index: 987

Text #1

Max Range: 5.6227. Min Range: -5.6227

Max Act: 3.8712. Min Act: -0.0000

Data Index: 1507120 (The Pile)

Max Activating Token Index: 98

Text #2

Max Range: 5.6227. Min Range: -5.6227

Max Act: 3.6356. Min Act: -0.0000

Data Index: 1335440 (The Pile)

Max Activating Token Index: 371

Text #3

Max Range: 5.6227. Min Range: -5.6227

Max Act: 3.2948. Min Act: -0.0000

Data Index: 1126800 (The Pile)

Max Activating Token Index: 901

Text #4

Max Range: 5.6227. Min Range: -5.6227

Max Act: 3.2709. Min Act: -0.0000

Data Index: 393441 (The Pile)

Max Activating Token Index: 413

Text #5

Max Range: 5.6227. Min Range: -5.6227

Max Act: 3.3478. Min Act: -0.0000

Data Index: 131985 (The Pile)

Max Activating Token Index: 485

Text #6

Max Range: 5.6227. Min Range: -5.6227

Max Act: 3.3328. Min Act: -0.0000

Data Index: 1035028 (The Pile)

Max Activating Token Index: 397

Text #7

Max Range: 5.6227. Min Range: -5.6227

Max Act: 3.1690. Min Act: -0.0000

Data Index: 1075386 (The Pile)

Max Activating Token Index: 46

Text #8

Max Range: 5.6227. Min Range: -5.6227

Max Act: 3.0664. Min Act: -0.0000

Data Index: 108368 (The Pile)

Max Activating Token Index: 66

Text #9

Max Range: 5.6227. Min Range: -5.6227

Max Act: 3.0725. Min Act: -0.0000

Data Index: 693015 (The Pile)

Max Activating Token Index: 216

Text #10

Max Range: 5.6227. Min Range: -5.6227

Max Act: 2.9870. Min Act: -0.0000

Data Index: 419055 (The Pile)

Max Activating Token Index: 173

Text #11

Max Range: 5.6227. Min Range: -5.6227

Max Act: 2.7949. Min Act: -0.0000

Data Index: 1623681 (The Pile)

Max Activating Token Index: 47

Text #12

Max Range: 5.6227. Min Range: -5.6227

Max Act: 3.0346. Min Act: -0.0000

Data Index: 1571824 (The Pile)

Max Activating Token Index: 779

Text #13

Max Range: 5.6227. Min Range: -5.6227

Max Act: 2.8657. Min Act: -0.0001

Data Index: 1901323 (The Pile)

Max Activating Token Index: 449

Text #14

Max Range: 5.6227. Min Range: -5.6227

Max Act: 2.7984. Min Act: -0.0000

Data Index: 468183 (The Pile)

Max Activating Token Index: 403

Text #15

Max Range: 5.6227. Min Range: -5.6227

Max Act: 2.7902. Min Act: -0.0000

Data Index: 488170 (The Pile)

Max Activating Token Index: 635

Text #16

Max Range: 5.6227. Min Range: -5.6227

Max Act: 2.6236. Min Act: -0.0000

Data Index: 1773477 (The Pile)

Max Activating Token Index: 270

Text #17

Max Range: 5.6227. Min Range: -5.6227

Max Act: 2.7342. Min Act: -0.0000

Data Index: 1842619 (The Pile)

Max Activating Token Index: 627

Text #18

Max Range: 5.6227. Min Range: -5.6227

Max Act: 2.7083. Min Act: -0.0001

Data Index: 651290 (The Pile)

Max Activating Token Index: 942

Text #19

Max Range: 5.6227. Min Range: -5.6227

Max Act: 2.7187. Min Act: -0.0000

Data Index: 1193078 (The Pile)

Max Activating Token Index: 82