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

Dataset: The Pile

Neuron 740 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: 3.2646. Min Range: -3.2646

Max Act: 3.2646. Min Act: 0.0000

Data Index: 580549 (The Pile)

Max Activating Token Index: 353

Text #1

Max Range: 3.2646. Min Range: -3.2646

Max Act: 3.0714. Min Act: -0.0000

Data Index: 302986 (The Pile)

Max Activating Token Index: 971

Text #2

Max Range: 3.2646. Min Range: -3.2646

Max Act: 2.9388. Min Act: -0.0000

Data Index: 1892949 (The Pile)

Max Activating Token Index: 928

Text #3

Max Range: 3.2646. Min Range: -3.2646

Max Act: 2.7544. Min Act: -0.0000

Data Index: 1060425 (The Pile)

Max Activating Token Index: 604

Text #4

Max Range: 3.2646. Min Range: -3.2646

Max Act: 2.9982. Min Act: -0.0000

Data Index: 1063666 (The Pile)

Max Activating Token Index: 737

Text #5

Max Range: 3.2646. Min Range: -3.2646

Max Act: 2.5724. Min Act: -0.0000

Data Index: 103762 (The Pile)

Max Activating Token Index: 633

Text #6

Max Range: 3.2646. Min Range: -3.2646

Max Act: 2.9205. Min Act: -0.0000

Data Index: 1812122 (The Pile)

Max Activating Token Index: 185

Text #7

Max Range: 3.2646. Min Range: -3.2646

Max Act: 2.8846. Min Act: -0.0000

Data Index: 1134871 (The Pile)

Max Activating Token Index: 529

Text #8

Max Range: 3.2646. Min Range: -3.2646

Max Act: 2.7823. Min Act: -0.0000

Data Index: 1805170 (The Pile)

Max Activating Token Index: 347

Text #9

Max Range: 3.2646. Min Range: -3.2646

Max Act: 2.7058. Min Act: -0.0000

Data Index: 906241 (The Pile)

Max Activating Token Index: 894

Text #10

Max Range: 3.2646. Min Range: -3.2646

Max Act: 2.7951. Min Act: -0.0000

Data Index: 1180529 (The Pile)

Max Activating Token Index: 594

Text #11

Max Range: 3.2646. Min Range: -3.2646

Max Act: 2.6390. Min Act: -0.0000

Data Index: 1856863 (The Pile)

Max Activating Token Index: 472

Text #12

Max Range: 3.2646. Min Range: -3.2646

Max Act: 2.7425. Min Act: -0.0000

Data Index: 1706000 (The Pile)

Max Activating Token Index: 599

Text #13

Max Range: 3.2646. Min Range: -3.2646

Max Act: 2.6152. Min Act: -0.0000

Data Index: 817847 (The Pile)

Max Activating Token Index: 552

Text #14

Max Range: 3.2646. Min Range: -3.2646

Max Act: 2.5044. Min Act: -0.0000

Data Index: 1954866 (The Pile)

Max Activating Token Index: 326

Text #15

Max Range: 3.2646. Min Range: -3.2646

Max Act: 2.7279. Min Act: -0.0000

Data Index: 91713 (The Pile)

Max Activating Token Index: 151

Text #16

Max Range: 3.2646. Min Range: -3.2646

Max Act: 2.5746. Min Act: -0.0000

Data Index: 421140 (The Pile)

Max Activating Token Index: 984

Text #17

Max Range: 3.2646. Min Range: -3.2646

Max Act: 2.5715. Min Act: -0.0000

Data Index: 170033 (The Pile)

Max Activating Token Index: 6

Text #18

Max Range: 3.2646. Min Range: -3.2646

Max Act: 2.5715. Min Act: -0.0000

Data Index: 124661 (The Pile)

Max Activating Token Index: 6

Text #19

Max Range: 3.2646. Min Range: -3.2646

Max Act: 2.6982. Min Act: -0.0000

Data Index: 1543136 (The Pile)

Max Activating Token Index: 551