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

Dataset: The Pile

Neuron 1508 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7331. Min Range: -1.7331

Max Act: 1.5354. Min Act: -0.0000

Data Index: 1462827 (The Pile)

Max Activating Token Index: 972

Text #1

Max Range: 1.7331. Min Range: -1.7331

Max Act: 1.6710. Min Act: -0.0000

Data Index: 1762394 (The Pile)

Max Activating Token Index: 315

Text #2

Max Range: 1.7331. Min Range: -1.7331

Max Act: 1.6636. Min Act: -0.0000

Data Index: 1004607 (The Pile)

Max Activating Token Index: 929

Text #3

Max Range: 1.7331. Min Range: -1.7331

Max Act: 1.7331. Min Act: -0.0000

Data Index: 1280671 (The Pile)

Max Activating Token Index: 419

Text #4

Max Range: 1.7331. Min Range: -1.7331

Max Act: 1.3240. Min Act: -0.0000

Data Index: 1606101 (The Pile)

Max Activating Token Index: 296

Text #5

Max Range: 1.7331. Min Range: -1.7331

Max Act: 1.3060. Min Act: -0.0000

Data Index: 1822518 (The Pile)

Max Activating Token Index: 385

Text #6

Max Range: 1.7331. Min Range: -1.7331

Max Act: 1.1032. Min Act: -0.0000

Data Index: 1007061 (The Pile)

Max Activating Token Index: 321

Text #7

Max Range: 1.7331. Min Range: -1.7331

Max Act: 1.1732. Min Act: -0.0000

Data Index: 144507 (The Pile)

Max Activating Token Index: 440

Text #8

Max Range: 1.7331. Min Range: -1.7331

Max Act: 1.0211. Min Act: -0.0001

Data Index: 860208 (The Pile)

Max Activating Token Index: 64

Text #9

Max Range: 1.7331. Min Range: -1.7331

Max Act: 0.9767. Min Act: -0.0000

Data Index: 116115 (The Pile)

Max Activating Token Index: 970

Text #10

Max Range: 1.7331. Min Range: -1.7331

Max Act: 0.9643. Min Act: -0.0000

Data Index: 709488 (The Pile)

Max Activating Token Index: 788

Text #11

Max Range: 1.7331. Min Range: -1.7331

Max Act: 0.7961. Min Act: -0.0000

Data Index: 795302 (The Pile)

Max Activating Token Index: 765

Text #12

Max Range: 1.7331. Min Range: -1.7331

Max Act: 0.9366. Min Act: -0.0000

Data Index: 878903 (The Pile)

Max Activating Token Index: 946

Text #13

Max Range: 1.7331. Min Range: -1.7331

Max Act: 0.8500. Min Act: -0.0000

Data Index: 1931552 (The Pile)

Max Activating Token Index: 232

Text #14

Max Range: 1.7331. Min Range: -1.7331

Max Act: 0.9227. Min Act: -0.0000

Data Index: 273691 (The Pile)

Max Activating Token Index: 776

Text #15

Max Range: 1.7331. Min Range: -1.7331

Max Act: 0.8818. Min Act: -0.0000

Data Index: 412090 (The Pile)

Max Activating Token Index: 927

Text #16

Max Range: 1.7331. Min Range: -1.7331

Max Act: 0.8685. Min Act: -0.0001

Data Index: 1951022 (The Pile)

Max Activating Token Index: 101

Text #17

Max Range: 1.7331. Min Range: -1.7331

Max Act: 0.9064. Min Act: -0.0000

Data Index: 659026 (The Pile)

Max Activating Token Index: 599

Text #18

Max Range: 1.7331. Min Range: -1.7331

Max Act: 0.8864. Min Act: -0.0000

Data Index: 241512 (The Pile)

Max Activating Token Index: 931

Text #19

Max Range: 1.7331. Min Range: -1.7331

Max Act: 0.9647. Min Act: -0.0000

Data Index: 762778 (The Pile)

Max Activating Token Index: 1019