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

Dataset: The Pile

Neuron 2899 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.3435. Min Range: -1.3435

Max Act: 1.3435. Min Act: -0.0000

Data Index: 264242 (The Pile)

Max Activating Token Index: 795

Text #1

Max Range: 1.3435. Min Range: -1.3435

Max Act: 0.9526. Min Act: -0.0000

Data Index: 1173285 (The Pile)

Max Activating Token Index: 588

Text #2

Max Range: 1.3435. Min Range: -1.3435

Max Act: 0.9907. Min Act: -0.0000

Data Index: 1724911 (The Pile)

Max Activating Token Index: 517

Text #3

Max Range: 1.3435. Min Range: -1.3435

Max Act: 1.0100. Min Act: -0.0000

Data Index: 1782647 (The Pile)

Max Activating Token Index: 111

Text #4

Max Range: 1.3435. Min Range: -1.3435

Max Act: 0.9640. Min Act: -0.0000

Data Index: 565480 (The Pile)

Max Activating Token Index: 115

Text #5

Max Range: 1.3435. Min Range: -1.3435

Max Act: 1.0009. Min Act: -0.0000

Data Index: 1005518 (The Pile)

Max Activating Token Index: 366

Text #6

Max Range: 1.3435. Min Range: -1.3435

Max Act: 0.9475. Min Act: -0.0000

Data Index: 236397 (The Pile)

Max Activating Token Index: 229

Text #7

Max Range: 1.3435. Min Range: -1.3435

Max Act: 0.9419. Min Act: -0.0000

Data Index: 1012356 (The Pile)

Max Activating Token Index: 972

Text #8

Max Range: 1.3435. Min Range: -1.3435

Max Act: 0.9377. Min Act: -0.0000

Data Index: 629006 (The Pile)

Max Activating Token Index: 315

Text #9

Max Range: 1.3435. Min Range: -1.3435

Max Act: 0.8518. Min Act: -0.0000

Data Index: 1345227 (The Pile)

Max Activating Token Index: 880

Text #10

Max Range: 1.3435. Min Range: -1.3435

Max Act: 0.8847. Min Act: -0.0000

Data Index: 1659250 (The Pile)

Max Activating Token Index: 523

Text #11

Max Range: 1.3435. Min Range: -1.3435

Max Act: 0.9620. Min Act: -0.0000

Data Index: 296090 (The Pile)

Max Activating Token Index: 477

Text #12

Max Range: 1.3435. Min Range: -1.3435

Max Act: 0.9414. Min Act: -0.0000

Data Index: 1658479 (The Pile)

Max Activating Token Index: 451

Text #13

Max Range: 1.3435. Min Range: -1.3435

Max Act: 0.9135. Min Act: -0.0000

Data Index: 1042907 (The Pile)

Max Activating Token Index: 136

Text #14

Max Range: 1.3435. Min Range: -1.3435

Max Act: 0.9731. Min Act: -0.0000

Data Index: 1961636 (The Pile)

Max Activating Token Index: 113

Text #15

Max Range: 1.3435. Min Range: -1.3435

Max Act: 0.8944. Min Act: -0.0000

Data Index: 575505 (The Pile)

Max Activating Token Index: 673

Text #16

Max Range: 1.3435. Min Range: -1.3435

Max Act: 0.9198. Min Act: -0.0000

Data Index: 1097438 (The Pile)

Max Activating Token Index: 586

Text #17

Max Range: 1.3435. Min Range: -1.3435

Max Act: 0.8598. Min Act: -0.0000

Data Index: 1876956 (The Pile)

Max Activating Token Index: 151

Text #18

Max Range: 1.3435. Min Range: -1.3435

Max Act: 0.9084. Min Act: -0.0000

Data Index: 581555 (The Pile)

Max Activating Token Index: 175

Text #19

Max Range: 1.3435. Min Range: -1.3435

Max Act: 0.8843. Min Act: -0.0000

Data Index: 344043 (The Pile)

Max Activating Token Index: 106