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

Dataset: The Pile

Neuron 3912 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9603. Min Range: -0.9603

Max Act: 0.9603. Min Act: -0.0000

Data Index: 1583082 (The Pile)

Max Activating Token Index: 429

Text #1

Max Range: 0.9603. Min Range: -0.9603

Max Act: 0.7400. Min Act: -0.0000

Data Index: 124886 (The Pile)

Max Activating Token Index: 756

Text #2

Max Range: 0.9603. Min Range: -0.9603

Max Act: 0.7718. Min Act: -0.0000

Data Index: 1957066 (The Pile)

Max Activating Token Index: 500

Text #3

Max Range: 0.9603. Min Range: -0.9603

Max Act: 0.6087. Min Act: -0.0000

Data Index: 517746 (The Pile)

Max Activating Token Index: 959

Text #4

Max Range: 0.9603. Min Range: -0.9603

Max Act: 0.6060. Min Act: -0.0000

Data Index: 219387 (The Pile)

Max Activating Token Index: 413

Text #5

Max Range: 0.9603. Min Range: -0.9603

Max Act: 0.5352. Min Act: -0.0000

Data Index: 351239 (The Pile)

Max Activating Token Index: 119

Text #6

Max Range: 0.9603. Min Range: -0.9603

Max Act: 0.5614. Min Act: -0.0000

Data Index: 1189767 (The Pile)

Max Activating Token Index: 917

Text #7

Max Range: 0.9603. Min Range: -0.9603

Max Act: 0.5469. Min Act: -0.0000

Data Index: 476354 (The Pile)

Max Activating Token Index: 984

Text #8

Max Range: 0.9603. Min Range: -0.9603

Max Act: 0.5125. Min Act: -0.0000

Data Index: 925199 (The Pile)

Max Activating Token Index: 749

Text #9

Max Range: 0.9603. Min Range: -0.9603

Max Act: 0.4939. Min Act: -0.0000

Data Index: 772452 (The Pile)

Max Activating Token Index: 810

Text #10

Max Range: 0.9603. Min Range: -0.9603

Max Act: 0.4729. Min Act: -0.0000

Data Index: 1114551 (The Pile)

Max Activating Token Index: 189

Text #11

Max Range: 0.9603. Min Range: -0.9603

Max Act: 0.4728. Min Act: -0.0000

Data Index: 1789685 (The Pile)

Max Activating Token Index: 864

Text #12

Max Range: 0.9603. Min Range: -0.9603

Max Act: 0.4656. Min Act: -0.0000

Data Index: 76061 (The Pile)

Max Activating Token Index: 686

Text #13

Max Range: 0.9603. Min Range: -0.9603

Max Act: 0.4559. Min Act: -0.0000

Data Index: 1215553 (The Pile)

Max Activating Token Index: 279

Text #14

Max Range: 0.9603. Min Range: -0.9603

Max Act: 0.4404. Min Act: -0.0000

Data Index: 1242207 (The Pile)

Max Activating Token Index: 346

Text #15

Max Range: 0.9603. Min Range: -0.9603

Max Act: 0.4125. Min Act: -0.0000

Data Index: 1136009 (The Pile)

Max Activating Token Index: 600

Text #16

Max Range: 0.9603. Min Range: -0.9603

Max Act: 0.4566. Min Act: -0.0000

Data Index: 426344 (The Pile)

Max Activating Token Index: 726

Text #17

Max Range: 0.9603. Min Range: -0.9603

Max Act: 0.4004. Min Act: -0.0000

Data Index: 931133 (The Pile)

Max Activating Token Index: 837

Text #18

Max Range: 0.9603. Min Range: -0.9603

Max Act: 0.4370. Min Act: -0.0000

Data Index: 1098864 (The Pile)

Max Activating Token Index: 133

Text #19

Max Range: 0.9603. Min Range: -0.9603

Max Act: 0.4006. Min Act: -0.0000

Data Index: 210352 (The Pile)

Max Activating Token Index: 817