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

Dataset: The Pile

Neuron 1599 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: 0.8966. Min Range: -0.8966

Max Act: 0.8303. Min Act: -0.0000

Data Index: 1914165 (The Pile)

Max Activating Token Index: 746

Text #1

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.8484. Min Act: -0.0000

Data Index: 963107 (The Pile)

Max Activating Token Index: 837

Text #2

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.8966. Min Act: -0.0000

Data Index: 648652 (The Pile)

Max Activating Token Index: 722

Text #3

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.7998. Min Act: -0.0000

Data Index: 570403 (The Pile)

Max Activating Token Index: 538

Text #4

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.8063. Min Act: -0.0000

Data Index: 1916897 (The Pile)

Max Activating Token Index: 477

Text #5

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.7882. Min Act: -0.0000

Data Index: 280195 (The Pile)

Max Activating Token Index: 662

Text #6

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.7853. Min Act: -0.0000

Data Index: 1354222 (The Pile)

Max Activating Token Index: 873

Text #7

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.7922. Min Act: -0.0000

Data Index: 1096045 (The Pile)

Max Activating Token Index: 218

Text #8

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.8331. Min Act: -0.0000

Data Index: 782239 (The Pile)

Max Activating Token Index: 53

Text #9

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.7803. Min Act: -0.0000

Data Index: 1178996 (The Pile)

Max Activating Token Index: 513

Text #10

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.7085. Min Act: -0.0000

Data Index: 965516 (The Pile)

Max Activating Token Index: 757

Text #11

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.7395. Min Act: -0.0000

Data Index: 284640 (The Pile)

Max Activating Token Index: 518

Text #12

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.7723. Min Act: -0.0000

Data Index: 811698 (The Pile)

Max Activating Token Index: 517

Text #13

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.7634. Min Act: -0.0000

Data Index: 621053 (The Pile)

Max Activating Token Index: 568

Text #14

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.7129. Min Act: -0.0000

Data Index: 1502143 (The Pile)

Max Activating Token Index: 349

Text #15

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.7698. Min Act: -0.0000

Data Index: 52036 (The Pile)

Max Activating Token Index: 563

Text #16

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.7322. Min Act: -0.0000

Data Index: 1970755 (The Pile)

Max Activating Token Index: 300

Text #17

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.7258. Min Act: -0.0000

Data Index: 740814 (The Pile)

Max Activating Token Index: 133

Text #18

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.7061. Min Act: -0.0000

Data Index: 111033 (The Pile)

Max Activating Token Index: 760

Text #19

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.7097. Min Act: -0.0000

Data Index: 1026157 (The Pile)

Max Activating Token Index: 133