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

Dataset: The Pile

Neuron 4179 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.5583. Min Act: -0.0000

Data Index: 282425 (The Pile)

Max Activating Token Index: 1004

Text #1

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.6307. Min Act: -0.0000

Data Index: 1293385 (The Pile)

Max Activating Token Index: 470

Text #2

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.5594. Min Act: -0.0000

Data Index: 267419 (The Pile)

Max Activating Token Index: 227

Text #3

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.5394. Min Act: -0.0000

Data Index: 568015 (The Pile)

Max Activating Token Index: 233

Text #4

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.5088. Min Act: -0.0000

Data Index: 509210 (The Pile)

Max Activating Token Index: 597

Text #5

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.4788. Min Act: -0.0000

Data Index: 1520710 (The Pile)

Max Activating Token Index: 636

Text #6

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.4734. Min Act: -0.0000

Data Index: 349366 (The Pile)

Max Activating Token Index: 371

Text #7

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.5369. Min Act: -0.0000

Data Index: 1632886 (The Pile)

Max Activating Token Index: 713

Text #8

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.4803. Min Act: -0.0000

Data Index: 1397173 (The Pile)

Max Activating Token Index: 424

Text #9

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.5130. Min Act: -0.0000

Data Index: 1221366 (The Pile)

Max Activating Token Index: 831

Text #10

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.4119. Min Act: -0.0000

Data Index: 720164 (The Pile)

Max Activating Token Index: 844

Text #11

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.4109. Min Act: -0.0000

Data Index: 814173 (The Pile)

Max Activating Token Index: 69

Text #12

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.4643. Min Act: -0.0000

Data Index: 1197119 (The Pile)

Max Activating Token Index: 763

Text #13

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.4573. Min Act: -0.0000

Data Index: 1312625 (The Pile)

Max Activating Token Index: 529

Text #14

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.5090. Min Act: -0.0000

Data Index: 592270 (The Pile)

Max Activating Token Index: 982

Text #15

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.4507. Min Act: -0.0000

Data Index: 871857 (The Pile)

Max Activating Token Index: 1003

Text #16

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.4308. Min Act: -0.0000

Data Index: 1318659 (The Pile)

Max Activating Token Index: 732

Text #17

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.4263. Min Act: -0.0000

Data Index: 672215 (The Pile)

Max Activating Token Index: 751

Text #18

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.4565. Min Act: -0.0000

Data Index: 1891032 (The Pile)

Max Activating Token Index: 135

Text #19

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.4049. Min Act: -0.0000

Data Index: 437697 (The Pile)

Max Activating Token Index: 103