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

Dataset: The Pile

Neuron 2303 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6463. Min Range: -1.6463

Max Act: 1.3122. Min Act: -0.0000

Data Index: 752086 (The Pile)

Max Activating Token Index: 597

Text #1

Max Range: 1.6463. Min Range: -1.6463

Max Act: 1.6463. Min Act: -0.0000

Data Index: 729139 (The Pile)

Max Activating Token Index: 521

Text #2

Max Range: 1.6463. Min Range: -1.6463

Max Act: 1.2461. Min Act: -0.0000

Data Index: 1516354 (The Pile)

Max Activating Token Index: 672

Text #3

Max Range: 1.6463. Min Range: -1.6463

Max Act: 1.2981. Min Act: -0.0000

Data Index: 1019747 (The Pile)

Max Activating Token Index: 155

Text #4

Max Range: 1.6463. Min Range: -1.6463

Max Act: 1.3947. Min Act: -0.0000

Data Index: 42950 (The Pile)

Max Activating Token Index: 763

Text #5

Max Range: 1.6463. Min Range: -1.6463

Max Act: 1.4600. Min Act: -0.0000

Data Index: 584849 (The Pile)

Max Activating Token Index: 453

Text #6

Max Range: 1.6463. Min Range: -1.6463

Max Act: 1.4463. Min Act: -0.0000

Data Index: 724590 (The Pile)

Max Activating Token Index: 667

Text #7

Max Range: 1.6463. Min Range: -1.6463

Max Act: 1.3878. Min Act: -0.0000

Data Index: 1972872 (The Pile)

Max Activating Token Index: 117

Text #8

Max Range: 1.6463. Min Range: -1.6463

Max Act: 1.3121. Min Act: -0.0000

Data Index: 112699 (The Pile)

Max Activating Token Index: 140

Text #9

Max Range: 1.6463. Min Range: -1.6463

Max Act: 1.0923. Min Act: -0.0000

Data Index: 1808088 (The Pile)

Max Activating Token Index: 521

Text #10

Max Range: 1.6463. Min Range: -1.6463

Max Act: 1.3048. Min Act: -0.0000

Data Index: 1314205 (The Pile)

Max Activating Token Index: 181

Text #11

Max Range: 1.6463. Min Range: -1.6463

Max Act: 1.4215. Min Act: -0.0000

Data Index: 839367 (The Pile)

Max Activating Token Index: 385

Text #12

Max Range: 1.6463. Min Range: -1.6463

Max Act: 1.4737. Min Act: -0.0000

Data Index: 357621 (The Pile)

Max Activating Token Index: 516

Text #13

Max Range: 1.6463. Min Range: -1.6463

Max Act: 1.3518. Min Act: -0.0000

Data Index: 715276 (The Pile)

Max Activating Token Index: 369

Text #14

Max Range: 1.6463. Min Range: -1.6463

Max Act: 1.3374. Min Act: -0.0000

Data Index: 1572565 (The Pile)

Max Activating Token Index: 658

Text #15

Max Range: 1.6463. Min Range: -1.6463

Max Act: 1.2928. Min Act: -0.0000

Data Index: 960428 (The Pile)

Max Activating Token Index: 736

Text #16

Max Range: 1.6463. Min Range: -1.6463

Max Act: 1.4150. Min Act: -0.0000

Data Index: 813698 (The Pile)

Max Activating Token Index: 127

Text #17

Max Range: 1.6463. Min Range: -1.6463

Max Act: 1.1655. Min Act: -0.0000

Data Index: 856144 (The Pile)

Max Activating Token Index: 493

Text #18

Max Range: 1.6463. Min Range: -1.6463

Max Act: 1.2731. Min Act: -0.0000

Data Index: 1322002 (The Pile)

Max Activating Token Index: 138

Text #19

Max Range: 1.6463. Min Range: -1.6463

Max Act: 1.5451. Min Act: -0.0000

Data Index: 746096 (The Pile)

Max Activating Token Index: 675