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

Dataset: The Pile

Neuron 4589 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: 1.2088. Min Range: -1.2088

Max Act: 1.2088. Min Act: -0.0000

Data Index: 1530731 (The Pile)

Max Activating Token Index: 68

Text #1

Max Range: 1.2088. Min Range: -1.2088

Max Act: 0.9004. Min Act: -0.0000

Data Index: 587061 (The Pile)

Max Activating Token Index: 539

Text #2

Max Range: 1.2088. Min Range: -1.2088

Max Act: 0.8147. Min Act: -0.0000

Data Index: 689179 (The Pile)

Max Activating Token Index: 304

Text #3

Max Range: 1.2088. Min Range: -1.2088

Max Act: 0.8226. Min Act: -0.0000

Data Index: 319166 (The Pile)

Max Activating Token Index: 409

Text #4

Max Range: 1.2088. Min Range: -1.2088

Max Act: 0.7844. Min Act: -0.0000

Data Index: 1199488 (The Pile)

Max Activating Token Index: 154

Text #5

Max Range: 1.2088. Min Range: -1.2088

Max Act: 0.7288. Min Act: -0.0000

Data Index: 1938315 (The Pile)

Max Activating Token Index: 152

Text #6

Max Range: 1.2088. Min Range: -1.2088

Max Act: 0.7683. Min Act: -0.0000

Data Index: 1458714 (The Pile)

Max Activating Token Index: 536

Text #7

Max Range: 1.2088. Min Range: -1.2088

Max Act: 0.7544. Min Act: -0.0000

Data Index: 295348 (The Pile)

Max Activating Token Index: 943

Text #8

Max Range: 1.2088. Min Range: -1.2088

Max Act: 0.7026. Min Act: -0.0000

Data Index: 1008147 (The Pile)

Max Activating Token Index: 822

Text #9

Max Range: 1.2088. Min Range: -1.2088

Max Act: 0.6199. Min Act: -0.0000

Data Index: 374612 (The Pile)

Max Activating Token Index: 281

Text #10

Max Range: 1.2088. Min Range: -1.2088

Max Act: 0.6216. Min Act: -0.0000

Data Index: 1054886 (The Pile)

Max Activating Token Index: 362

Text #11

Max Range: 1.2088. Min Range: -1.2088

Max Act: 0.6199. Min Act: -0.0000

Data Index: 582526 (The Pile)

Max Activating Token Index: 651

Text #12

Max Range: 1.2088. Min Range: -1.2088

Max Act: 0.6354. Min Act: -0.0000

Data Index: 566546 (The Pile)

Max Activating Token Index: 961

Text #13

Max Range: 1.2088. Min Range: -1.2088

Max Act: 0.5951. Min Act: -0.0000

Data Index: 355276 (The Pile)

Max Activating Token Index: 977

Text #14

Max Range: 1.2088. Min Range: -1.2088

Max Act: 0.6049. Min Act: -0.0000

Data Index: 1510838 (The Pile)

Max Activating Token Index: 86

Text #15

Max Range: 1.2088. Min Range: -1.2088

Max Act: 0.6233. Min Act: -0.0000

Data Index: 1840846 (The Pile)

Max Activating Token Index: 319

Text #16

Max Range: 1.2088. Min Range: -1.2088

Max Act: 0.5916. Min Act: -0.0000

Data Index: 1349166 (The Pile)

Max Activating Token Index: 554

Text #17

Max Range: 1.2088. Min Range: -1.2088

Max Act: 0.5699. Min Act: -0.0000

Data Index: 1802534 (The Pile)

Max Activating Token Index: 957

Text #18

Max Range: 1.2088. Min Range: -1.2088

Max Act: 0.5258. Min Act: -0.0000

Data Index: 483188 (The Pile)

Max Activating Token Index: 569

Text #19

Max Range: 1.2088. Min Range: -1.2088

Max Act: 0.5512. Min Act: -0.0000

Data Index: 1387313 (The Pile)

Max Activating Token Index: 605