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

Dataset: The Pile

Neuron 1767 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.7651. Min Act: -0.0000

Data Index: 1344332 (The Pile)

Max Activating Token Index: 143

Text #1

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.6637. Min Act: -0.0000

Data Index: 1139379 (The Pile)

Max Activating Token Index: 795

Text #2

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.6473. Min Act: -0.0000

Data Index: 320021 (The Pile)

Max Activating Token Index: 194

Text #3

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.6668. Min Act: -0.0000

Data Index: 516218 (The Pile)

Max Activating Token Index: 175

Text #4

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.6781. Min Act: -0.0000

Data Index: 666280 (The Pile)

Max Activating Token Index: 662

Text #5

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.6084. Min Act: -0.0000

Data Index: 1063466 (The Pile)

Max Activating Token Index: 101

Text #6

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.6468. Min Act: -0.0000

Data Index: 1286067 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.6064. Min Act: -0.0000

Data Index: 641751 (The Pile)

Max Activating Token Index: 231

Text #8

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.5825. Min Act: -0.0000

Data Index: 892924 (The Pile)

Max Activating Token Index: 285

Text #9

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.5833. Min Act: -0.0000

Data Index: 1914302 (The Pile)

Max Activating Token Index: 291

Text #10

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.5784. Min Act: -0.0000

Data Index: 1062919 (The Pile)

Max Activating Token Index: 994

Text #11

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.5385. Min Act: -0.0000

Data Index: 895013 (The Pile)

Max Activating Token Index: 772

Text #12

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.5780. Min Act: -0.0000

Data Index: 744731 (The Pile)

Max Activating Token Index: 730

Text #13

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.5543. Min Act: -0.0000

Data Index: 7799 (The Pile)

Max Activating Token Index: 919

Text #14

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.5490. Min Act: -0.0000

Data Index: 230514 (The Pile)

Max Activating Token Index: 316

Text #15

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.5514. Min Act: -0.0000

Data Index: 126026 (The Pile)

Max Activating Token Index: 621

Text #16

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.5500. Min Act: -0.0000

Data Index: 1123663 (The Pile)

Max Activating Token Index: 292

Text #17

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.5519. Min Act: -0.0000

Data Index: 61703 (The Pile)

Max Activating Token Index: 940

Text #18

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.5490. Min Act: -0.0000

Data Index: 1708471 (The Pile)

Max Activating Token Index: 765

Text #19

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.5270. Min Act: -0.0000

Data Index: 811223 (The Pile)

Max Activating Token Index: 61