Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 434 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.2056. Min Range: -1.2056

Max Act: 1.2056. Min Act: -0.0000

Data Index: 940751 (The Pile)

Max Activating Token Index: 258

Text #1

Max Range: 1.2056. Min Range: -1.2056

Max Act: 1.0174. Min Act: -0.0000

Data Index: 890196 (The Pile)

Max Activating Token Index: 326

Text #2

Max Range: 1.2056. Min Range: -1.2056

Max Act: 0.9082. Min Act: -0.0000

Data Index: 1038779 (The Pile)

Max Activating Token Index: 99

Text #3

Max Range: 1.2056. Min Range: -1.2056

Max Act: 0.9564. Min Act: -0.0000

Data Index: 646453 (The Pile)

Max Activating Token Index: 359

Text #4

Max Range: 1.2056. Min Range: -1.2056

Max Act: 0.8682. Min Act: -0.0000

Data Index: 786151 (The Pile)

Max Activating Token Index: 555

Text #5

Max Range: 1.2056. Min Range: -1.2056

Max Act: 0.8860. Min Act: -0.0000

Data Index: 479873 (The Pile)

Max Activating Token Index: 708

Text #6

Max Range: 1.2056. Min Range: -1.2056

Max Act: 0.8656. Min Act: -0.0000

Data Index: 1632289 (The Pile)

Max Activating Token Index: 906

Text #7

Max Range: 1.2056. Min Range: -1.2056

Max Act: 0.8675. Min Act: -0.0000

Data Index: 1076201 (The Pile)

Max Activating Token Index: 360

Text #8

Max Range: 1.2056. Min Range: -1.2056

Max Act: 0.8600. Min Act: -0.0000

Data Index: 1902013 (The Pile)

Max Activating Token Index: 704

Text #9

Max Range: 1.2056. Min Range: -1.2056

Max Act: 0.8184. Min Act: -0.0000

Data Index: 1691120 (The Pile)

Max Activating Token Index: 803

Text #10

Max Range: 1.2056. Min Range: -1.2056

Max Act: 0.8581. Min Act: -0.0000

Data Index: 639521 (The Pile)

Max Activating Token Index: 813

Text #11

Max Range: 1.2056. Min Range: -1.2056

Max Act: 0.8349. Min Act: -0.0000

Data Index: 111772 (The Pile)

Max Activating Token Index: 403

Text #12

Max Range: 1.2056. Min Range: -1.2056

Max Act: 0.8227. Min Act: -0.0000

Data Index: 232200 (The Pile)

Max Activating Token Index: 245

Text #13

Max Range: 1.2056. Min Range: -1.2056

Max Act: 0.7976. Min Act: -0.0000

Data Index: 212242 (The Pile)

Max Activating Token Index: 661

Text #14

Max Range: 1.2056. Min Range: -1.2056

Max Act: 0.8195. Min Act: -0.0000

Data Index: 387463 (The Pile)

Max Activating Token Index: 55

Text #15

Max Range: 1.2056. Min Range: -1.2056

Max Act: 0.8121. Min Act: -0.0000

Data Index: 708768 (The Pile)

Max Activating Token Index: 965

Text #16

Max Range: 1.2056. Min Range: -1.2056

Max Act: 0.8181. Min Act: -0.0000

Data Index: 922083 (The Pile)

Max Activating Token Index: 489

Text #17

Max Range: 1.2056. Min Range: -1.2056

Max Act: 0.7985. Min Act: -0.0000

Data Index: 323360 (The Pile)

Max Activating Token Index: 139

Text #18

Max Range: 1.2056. Min Range: -1.2056

Max Act: 0.7716. Min Act: -0.0000

Data Index: 98294 (The Pile)

Max Activating Token Index: 949

Text #19

Max Range: 1.2056. Min Range: -1.2056

Max Act: 0.7856. Min Act: -0.0000

Data Index: 614048 (The Pile)

Max Activating Token Index: 506