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

Dataset: The Pile

Neuron 3385 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: 0.7067. Min Range: -0.7067

Max Act: 0.7067. Min Act: -0.0000

Data Index: 1886269 (The Pile)

Max Activating Token Index: 776

Text #1

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.6123. Min Act: -0.0000

Data Index: 1384 (The Pile)

Max Activating Token Index: 551

Text #2

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.5219. Min Act: -0.0000

Data Index: 1438189 (The Pile)

Max Activating Token Index: 805

Text #3

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.5880. Min Act: -0.0000

Data Index: 1295709 (The Pile)

Max Activating Token Index: 577

Text #4

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.5526. Min Act: -0.0000

Data Index: 1879482 (The Pile)

Max Activating Token Index: 217

Text #5

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.5385. Min Act: -0.0000

Data Index: 819385 (The Pile)

Max Activating Token Index: 749

Text #6

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.5341. Min Act: -0.0000

Data Index: 280346 (The Pile)

Max Activating Token Index: 215

Text #7

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.5480. Min Act: -0.0000

Data Index: 29328 (The Pile)

Max Activating Token Index: 264

Text #8

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.5846. Min Act: -0.0000

Data Index: 1398057 (The Pile)

Max Activating Token Index: 609

Text #9

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.4956. Min Act: -0.0000

Data Index: 407947 (The Pile)

Max Activating Token Index: 26

Text #10

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.4974. Min Act: -0.0000

Data Index: 817386 (The Pile)

Max Activating Token Index: 892

Text #11

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.5039. Min Act: -0.0000

Data Index: 1758382 (The Pile)

Max Activating Token Index: 292

Text #12

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.5569. Min Act: -0.0000

Data Index: 1873235 (The Pile)

Max Activating Token Index: 382

Text #13

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.5319. Min Act: -0.0000

Data Index: 1314858 (The Pile)

Max Activating Token Index: 600

Text #14

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.5172. Min Act: -0.0000

Data Index: 910961 (The Pile)

Max Activating Token Index: 329

Text #15

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.4413. Min Act: -0.0001

Data Index: 189289 (The Pile)

Max Activating Token Index: 132

Text #16

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.4535. Min Act: -0.0000

Data Index: 1588368 (The Pile)

Max Activating Token Index: 98

Text #17

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.4520. Min Act: -0.0000

Data Index: 1731500 (The Pile)

Max Activating Token Index: 33

Text #18

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.4694. Min Act: -0.0000

Data Index: 1885348 (The Pile)

Max Activating Token Index: 19

Text #19

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.5707. Min Act: 0.0000

Data Index: 1204217 (The Pile)

Max Activating Token Index: 1015