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

Dataset: The Pile

Neuron 3263 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.8212. Min Act: -0.0000

Data Index: 339480 (The Pile)

Max Activating Token Index: 85

Text #1

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.7450. Min Act: -0.0000

Data Index: 504959 (The Pile)

Max Activating Token Index: 763

Text #2

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.7773. Min Act: -0.0000

Data Index: 487060 (The Pile)

Max Activating Token Index: 759

Text #3

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.5967. Min Act: -0.0000

Data Index: 1072213 (The Pile)

Max Activating Token Index: 1008

Text #4

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.6486. Min Act: -0.0000

Data Index: 1626732 (The Pile)

Max Activating Token Index: 263

Text #5

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.6353. Min Act: -0.0000

Data Index: 694829 (The Pile)

Max Activating Token Index: 174

Text #6

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.5956. Min Act: -0.0000

Data Index: 1792942 (The Pile)

Max Activating Token Index: 928

Text #7

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.5727. Min Act: -0.0000

Data Index: 1720505 (The Pile)

Max Activating Token Index: 603

Text #8

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.5734. Min Act: -0.0000

Data Index: 876352 (The Pile)

Max Activating Token Index: 760

Text #9

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.6027. Min Act: 0.0000

Data Index: 1370180 (The Pile)

Max Activating Token Index: 192

Text #10

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.6650. Min Act: -0.0000

Data Index: 276400 (The Pile)

Max Activating Token Index: 177

Text #11

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.6368. Min Act: -0.0000

Data Index: 1999673 (The Pile)

Max Activating Token Index: 714

Text #12

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.6624. Min Act: -0.0000

Data Index: 1776520 (The Pile)

Max Activating Token Index: 15

Text #13

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.6023. Min Act: -0.0000

Data Index: 1755763 (The Pile)

Max Activating Token Index: 937

Text #14

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.5585. Min Act: -0.0000

Data Index: 1588497 (The Pile)

Max Activating Token Index: 219

Text #15

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.5587. Min Act: -0.0000

Data Index: 499085 (The Pile)

Max Activating Token Index: 391

Text #16

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.5350. Min Act: -0.0000

Data Index: 1656387 (The Pile)

Max Activating Token Index: 222

Text #17

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.5145. Min Act: -0.0000

Data Index: 1567177 (The Pile)

Max Activating Token Index: 157

Text #18

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.5496. Min Act: -0.0000

Data Index: 651770 (The Pile)

Max Activating Token Index: 603

Text #19

Max Range: 0.8212. Min Range: -0.8212

Max Act: 0.6024. Min Act: -0.0000

Data Index: 983370 (The Pile)

Max Activating Token Index: 815