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

Dataset: The Pile

Neuron 572 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5559. Min Range: -0.5559

Max Act: 0.5559. Min Act: -0.0000

Data Index: 171129 (The Pile)

Max Activating Token Index: 906

Text #1

Max Range: 0.5559. Min Range: -0.5559

Max Act: 0.5329. Min Act: -0.0000

Data Index: 327650 (The Pile)

Max Activating Token Index: 413

Text #2

Max Range: 0.5559. Min Range: -0.5559

Max Act: 0.5223. Min Act: -0.0000

Data Index: 1837934 (The Pile)

Max Activating Token Index: 782

Text #3

Max Range: 0.5559. Min Range: -0.5559

Max Act: 0.5033. Min Act: -0.0000

Data Index: 1791269 (The Pile)

Max Activating Token Index: 422

Text #4

Max Range: 0.5559. Min Range: -0.5559

Max Act: 0.4826. Min Act: -0.0000

Data Index: 1217136 (The Pile)

Max Activating Token Index: 182

Text #5

Max Range: 0.5559. Min Range: -0.5559

Max Act: 0.4653. Min Act: -0.0000

Data Index: 1916811 (The Pile)

Max Activating Token Index: 417

Text #6

Max Range: 0.5559. Min Range: -0.5559

Max Act: 0.4745. Min Act: -0.0000

Data Index: 298150 (The Pile)

Max Activating Token Index: 741

Text #7

Max Range: 0.5559. Min Range: -0.5559

Max Act: 0.4699. Min Act: -0.0000

Data Index: 430530 (The Pile)

Max Activating Token Index: 115

Text #8

Max Range: 0.5559. Min Range: -0.5559

Max Act: 0.4518. Min Act: -0.0000

Data Index: 733463 (The Pile)

Max Activating Token Index: 719

Text #9

Max Range: 0.5559. Min Range: -0.5559

Max Act: 0.4219. Min Act: -0.0000

Data Index: 1985924 (The Pile)

Max Activating Token Index: 747

Text #10

Max Range: 0.5559. Min Range: -0.5559

Max Act: 0.4441. Min Act: -0.0000

Data Index: 1025245 (The Pile)

Max Activating Token Index: 239

Text #11

Max Range: 0.5559. Min Range: -0.5559

Max Act: 0.4319. Min Act: -0.0000

Data Index: 1292160 (The Pile)

Max Activating Token Index: 833

Text #12

Max Range: 0.5559. Min Range: -0.5559

Max Act: 0.4208. Min Act: -0.0000

Data Index: 1989008 (The Pile)

Max Activating Token Index: 116

Text #13

Max Range: 0.5559. Min Range: -0.5559

Max Act: 0.4599. Min Act: -0.0000

Data Index: 1798367 (The Pile)

Max Activating Token Index: 1016

Text #14

Max Range: 0.5559. Min Range: -0.5559

Max Act: 0.3927. Min Act: -0.0000

Data Index: 1089158 (The Pile)

Max Activating Token Index: 124

Text #15

Max Range: 0.5559. Min Range: -0.5559

Max Act: 0.4125. Min Act: 0.0000

Data Index: 572310 (The Pile)

Max Activating Token Index: 330

Text #16

Max Range: 0.5559. Min Range: -0.5559

Max Act: 0.4004. Min Act: -0.0000

Data Index: 753833 (The Pile)

Max Activating Token Index: 730

Text #17

Max Range: 0.5559. Min Range: -0.5559

Max Act: 0.4045. Min Act: -0.0000

Data Index: 499165 (The Pile)

Max Activating Token Index: 681

Text #18

Max Range: 0.5559. Min Range: -0.5559

Max Act: 0.3917. Min Act: -0.0000

Data Index: 35215 (The Pile)

Max Activating Token Index: 674

Text #19

Max Range: 0.5559. Min Range: -0.5559

Max Act: 0.3749. Min Act: -0.0000

Data Index: 1255257 (The Pile)

Max Activating Token Index: 994