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

Dataset: The Pile

Neuron 3152 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: 1.0352. Min Range: -1.0352

Max Act: 1.0352. Min Act: -0.0000

Data Index: 113208 (The Pile)

Max Activating Token Index: 85

Text #1

Max Range: 1.0352. Min Range: -1.0352

Max Act: 0.9949. Min Act: -0.0000

Data Index: 165666 (The Pile)

Max Activating Token Index: 152

Text #2

Max Range: 1.0352. Min Range: -1.0352

Max Act: 0.9206. Min Act: -0.0000

Data Index: 30001 (The Pile)

Max Activating Token Index: 868

Text #3

Max Range: 1.0352. Min Range: -1.0352

Max Act: 0.9374. Min Act: -0.0000

Data Index: 765828 (The Pile)

Max Activating Token Index: 216

Text #4

Max Range: 1.0352. Min Range: -1.0352

Max Act: 0.8472. Min Act: -0.0000

Data Index: 1786051 (The Pile)

Max Activating Token Index: 498

Text #5

Max Range: 1.0352. Min Range: -1.0352

Max Act: 0.8518. Min Act: -0.0000

Data Index: 244250 (The Pile)

Max Activating Token Index: 795

Text #6

Max Range: 1.0352. Min Range: -1.0352

Max Act: 0.9085. Min Act: -0.0000

Data Index: 1487682 (The Pile)

Max Activating Token Index: 837

Text #7

Max Range: 1.0352. Min Range: -1.0352

Max Act: 0.9130. Min Act: -0.0000

Data Index: 1261746 (The Pile)

Max Activating Token Index: 785

Text #8

Max Range: 1.0352. Min Range: -1.0352

Max Act: 0.8783. Min Act: -0.0000

Data Index: 1520921 (The Pile)

Max Activating Token Index: 1016

Text #9

Max Range: 1.0352. Min Range: -1.0352

Max Act: 0.8873. Min Act: -0.0000

Data Index: 547183 (The Pile)

Max Activating Token Index: 634

Text #10

Max Range: 1.0352. Min Range: -1.0352

Max Act: 0.8739. Min Act: -0.0000

Data Index: 112187 (The Pile)

Max Activating Token Index: 232

Text #11

Max Range: 1.0352. Min Range: -1.0352

Max Act: 0.8303. Min Act: -0.0000

Data Index: 318303 (The Pile)

Max Activating Token Index: 472

Text #12

Max Range: 1.0352. Min Range: -1.0352

Max Act: 0.8445. Min Act: -0.0000

Data Index: 969912 (The Pile)

Max Activating Token Index: 147

Text #13

Max Range: 1.0352. Min Range: -1.0352

Max Act: 0.8099. Min Act: -0.0000

Data Index: 884511 (The Pile)

Max Activating Token Index: 128

Text #14

Max Range: 1.0352. Min Range: -1.0352

Max Act: 0.7735. Min Act: -0.0000

Data Index: 1467922 (The Pile)

Max Activating Token Index: 786

Text #15

Max Range: 1.0352. Min Range: -1.0352

Max Act: 0.7619. Min Act: -0.0000

Data Index: 1814149 (The Pile)

Max Activating Token Index: 1008

Text #16

Max Range: 1.0352. Min Range: -1.0352

Max Act: 0.7583. Min Act: -0.0000

Data Index: 1372760 (The Pile)

Max Activating Token Index: 163

Text #17

Max Range: 1.0352. Min Range: -1.0352

Max Act: 0.8213. Min Act: -0.0000

Data Index: 1482402 (The Pile)

Max Activating Token Index: 576

Text #18

Max Range: 1.0352. Min Range: -1.0352

Max Act: 0.7918. Min Act: -0.0000

Data Index: 1745142 (The Pile)

Max Activating Token Index: 228

Text #19

Max Range: 1.0352. Min Range: -1.0352

Max Act: 0.7867. Min Act: -0.0000

Data Index: 1206925 (The Pile)

Max Activating Token Index: 398