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

Dataset: The Pile

Neuron 4965 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7897. Min Range: -0.7897

Max Act: 0.7897. Min Act: -0.0000

Data Index: 277390 (The Pile)

Max Activating Token Index: 796

Text #1

Max Range: 0.7897. Min Range: -0.7897

Max Act: 0.7728. Min Act: -0.0000

Data Index: 1767896 (The Pile)

Max Activating Token Index: 951

Text #2

Max Range: 0.7897. Min Range: -0.7897

Max Act: 0.7447. Min Act: -0.0000

Data Index: 395172 (The Pile)

Max Activating Token Index: 521

Text #3

Max Range: 0.7897. Min Range: -0.7897

Max Act: 0.6761. Min Act: -0.0000

Data Index: 840802 (The Pile)

Max Activating Token Index: 695

Text #4

Max Range: 0.7897. Min Range: -0.7897

Max Act: 0.6701. Min Act: -0.0000

Data Index: 184236 (The Pile)

Max Activating Token Index: 297

Text #5

Max Range: 0.7897. Min Range: -0.7897

Max Act: 0.6982. Min Act: -0.0000

Data Index: 1059527 (The Pile)

Max Activating Token Index: 249

Text #6

Max Range: 0.7897. Min Range: -0.7897

Max Act: 0.6765. Min Act: -0.0000

Data Index: 1915460 (The Pile)

Max Activating Token Index: 790

Text #7

Max Range: 0.7897. Min Range: -0.7897

Max Act: 0.6183. Min Act: -0.0000

Data Index: 1147371 (The Pile)

Max Activating Token Index: 853

Text #8

Max Range: 0.7897. Min Range: -0.7897

Max Act: 0.6061. Min Act: -0.0000

Data Index: 492202 (The Pile)

Max Activating Token Index: 585

Text #9

Max Range: 0.7897. Min Range: -0.7897

Max Act: 0.6701. Min Act: -0.0000

Data Index: 1130743 (The Pile)

Max Activating Token Index: 148

Text #10

Max Range: 0.7897. Min Range: -0.7897

Max Act: 0.6889. Min Act: -0.0000

Data Index: 926376 (The Pile)

Max Activating Token Index: 96

Text #11

Max Range: 0.7897. Min Range: -0.7897

Max Act: 0.6860. Min Act: -0.0000

Data Index: 622410 (The Pile)

Max Activating Token Index: 242

Text #12

Max Range: 0.7897. Min Range: -0.7897

Max Act: 0.6147. Min Act: -0.0000

Data Index: 1911361 (The Pile)

Max Activating Token Index: 891

Text #13

Max Range: 0.7897. Min Range: -0.7897

Max Act: 0.5994. Min Act: -0.0000

Data Index: 45662 (The Pile)

Max Activating Token Index: 937

Text #14

Max Range: 0.7897. Min Range: -0.7897

Max Act: 0.7043. Min Act: 0.0000

Data Index: 1380989 (The Pile)

Max Activating Token Index: 1016

Text #15

Max Range: 0.7897. Min Range: -0.7897

Max Act: 0.5349. Min Act: -0.0000

Data Index: 1860065 (The Pile)

Max Activating Token Index: 886

Text #16

Max Range: 0.7897. Min Range: -0.7897

Max Act: 0.6464. Min Act: -0.0000

Data Index: 690206 (The Pile)

Max Activating Token Index: 279

Text #17

Max Range: 0.7897. Min Range: -0.7897

Max Act: 0.5994. Min Act: -0.0000

Data Index: 1992548 (The Pile)

Max Activating Token Index: 717

Text #18

Max Range: 0.7897. Min Range: -0.7897

Max Act: 0.5708. Min Act: -0.0000

Data Index: 33306 (The Pile)

Max Activating Token Index: 670

Text #19

Max Range: 0.7897. Min Range: -0.7897

Max Act: 0.5974. Min Act: -0.0000

Data Index: 219021 (The Pile)

Max Activating Token Index: 690