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

Dataset: The Pile

Neuron 487 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: 0.7520. Min Range: -0.7520

Max Act: 0.6952. Min Act: -0.0000

Data Index: 765449 (The Pile)

Max Activating Token Index: 81

Text #1

Max Range: 0.7520. Min Range: -0.7520

Max Act: 0.7473. Min Act: -0.0000

Data Index: 64126 (The Pile)

Max Activating Token Index: 127

Text #2

Max Range: 0.7520. Min Range: -0.7520

Max Act: 0.7020. Min Act: -0.0000

Data Index: 1986428 (The Pile)

Max Activating Token Index: 244

Text #3

Max Range: 0.7520. Min Range: -0.7520

Max Act: 0.6714. Min Act: -0.0000

Data Index: 1963095 (The Pile)

Max Activating Token Index: 51

Text #4

Max Range: 0.7520. Min Range: -0.7520

Max Act: 0.6468. Min Act: -0.0000

Data Index: 855549 (The Pile)

Max Activating Token Index: 64

Text #5

Max Range: 0.7520. Min Range: -0.7520

Max Act: 0.7520. Min Act: -0.0000

Data Index: 1734875 (The Pile)

Max Activating Token Index: 60

Text #6

Max Range: 0.7520. Min Range: -0.7520

Max Act: 0.6689. Min Act: -0.0000

Data Index: 1126219 (The Pile)

Max Activating Token Index: 53

Text #7

Max Range: 0.7520. Min Range: -0.7520

Max Act: 0.6648. Min Act: -0.0000

Data Index: 125776 (The Pile)

Max Activating Token Index: 762

Text #8

Max Range: 0.7520. Min Range: -0.7520

Max Act: 0.5615. Min Act: -0.0000

Data Index: 1105795 (The Pile)

Max Activating Token Index: 947

Text #9

Max Range: 0.7520. Min Range: -0.7520

Max Act: 0.6710. Min Act: -0.0000

Data Index: 134419 (The Pile)

Max Activating Token Index: 280

Text #10

Max Range: 0.7520. Min Range: -0.7520

Max Act: 0.6953. Min Act: -0.0000

Data Index: 1181514 (The Pile)

Max Activating Token Index: 547

Text #11

Max Range: 0.7520. Min Range: -0.7520

Max Act: 0.5878. Min Act: -0.0000

Data Index: 535908 (The Pile)

Max Activating Token Index: 690

Text #12

Max Range: 0.7520. Min Range: -0.7520

Max Act: 0.6220. Min Act: -0.0000

Data Index: 718157 (The Pile)

Max Activating Token Index: 712

Text #13

Max Range: 0.7520. Min Range: -0.7520

Max Act: 0.6538. Min Act: -0.0000

Data Index: 1547948 (The Pile)

Max Activating Token Index: 119

Text #14

Max Range: 0.7520. Min Range: -0.7520

Max Act: 0.6648. Min Act: -0.0000

Data Index: 795970 (The Pile)

Max Activating Token Index: 545

Text #15

Max Range: 0.7520. Min Range: -0.7520

Max Act: 0.6151. Min Act: -0.0000

Data Index: 1582417 (The Pile)

Max Activating Token Index: 161

Text #16

Max Range: 0.7520. Min Range: -0.7520

Max Act: 0.6018. Min Act: -0.0000

Data Index: 989403 (The Pile)

Max Activating Token Index: 77

Text #17

Max Range: 0.7520. Min Range: -0.7520

Max Act: 0.6985. Min Act: -0.0000

Data Index: 256121 (The Pile)

Max Activating Token Index: 734

Text #18

Max Range: 0.7520. Min Range: -0.7520

Max Act: 0.6040. Min Act: -0.0000

Data Index: 1859348 (The Pile)

Max Activating Token Index: 709

Text #19

Max Range: 0.7520. Min Range: -0.7520

Max Act: 0.6501. Min Act: -0.0000

Data Index: 1164819 (The Pile)

Max Activating Token Index: 856