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

Dataset: The Pile

Neuron 2957 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: 1.4948. Min Range: -1.4948

Max Act: 1.3028. Min Act: -0.0000

Data Index: 1555358 (The Pile)

Max Activating Token Index: 758

Text #1

Max Range: 1.4948. Min Range: -1.4948

Max Act: 1.4948. Min Act: -0.0000

Data Index: 66496 (The Pile)

Max Activating Token Index: 89

Text #2

Max Range: 1.4948. Min Range: -1.4948

Max Act: 1.0307. Min Act: -0.0000

Data Index: 191223 (The Pile)

Max Activating Token Index: 59

Text #3

Max Range: 1.4948. Min Range: -1.4948

Max Act: 1.0607. Min Act: -0.0000

Data Index: 1415577 (The Pile)

Max Activating Token Index: 10

Text #4

Max Range: 1.4948. Min Range: -1.4948

Max Act: 1.0298. Min Act: -0.0000

Data Index: 1028254 (The Pile)

Max Activating Token Index: 71

Text #5

Max Range: 1.4948. Min Range: -1.4948

Max Act: 1.0112. Min Act: -0.0000

Data Index: 1828850 (The Pile)

Max Activating Token Index: 397

Text #6

Max Range: 1.4948. Min Range: -1.4948

Max Act: 0.9736. Min Act: -0.0000

Data Index: 1397661 (The Pile)

Max Activating Token Index: 25

Text #7

Max Range: 1.4948. Min Range: -1.4948

Max Act: 0.9677. Min Act: 0.0000

Data Index: 1874928 (The Pile)

Max Activating Token Index: 437

Text #8

Max Range: 1.4948. Min Range: -1.4948

Max Act: 1.0209. Min Act: -0.0000

Data Index: 1575503 (The Pile)

Max Activating Token Index: 221

Text #9

Max Range: 1.4948. Min Range: -1.4948

Max Act: 1.0086. Min Act: -0.0000

Data Index: 1389075 (The Pile)

Max Activating Token Index: 713

Text #10

Max Range: 1.4948. Min Range: -1.4948

Max Act: 0.8912. Min Act: -0.0000

Data Index: 1007243 (The Pile)

Max Activating Token Index: 139

Text #11

Max Range: 1.4948. Min Range: -1.4948

Max Act: 0.9834. Min Act: 0.0000

Data Index: 19323 (The Pile)

Max Activating Token Index: 712

Text #12

Max Range: 1.4948. Min Range: -1.4948

Max Act: 0.9333. Min Act: -0.0000

Data Index: 1083092 (The Pile)

Max Activating Token Index: 243

Text #13

Max Range: 1.4948. Min Range: -1.4948

Max Act: 0.9338. Min Act: -0.0000

Data Index: 60298 (The Pile)

Max Activating Token Index: 86

Text #14

Max Range: 1.4948. Min Range: -1.4948

Max Act: 0.9495. Min Act: -0.0000

Data Index: 296764 (The Pile)

Max Activating Token Index: 11

Text #15

Max Range: 1.4948. Min Range: -1.4948

Max Act: 0.9154. Min Act: -0.0000

Data Index: 124531 (The Pile)

Max Activating Token Index: 528

Text #16

Max Range: 1.4948. Min Range: -1.4948

Max Act: 0.9089. Min Act: -0.0000

Data Index: 1323563 (The Pile)

Max Activating Token Index: 510

Text #17

Max Range: 1.4948. Min Range: -1.4948

Max Act: 0.8502. Min Act: -0.0000

Data Index: 1514963 (The Pile)

Max Activating Token Index: 37

Text #18

Max Range: 1.4948. Min Range: -1.4948

Max Act: 0.9088. Min Act: -0.0000

Data Index: 1431749 (The Pile)

Max Activating Token Index: 899

Text #19

Max Range: 1.4948. Min Range: -1.4948

Max Act: 0.8372. Min Act: -0.0000

Data Index: 1307232 (The Pile)

Max Activating Token Index: 320