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

Dataset: The Pile

Neuron 2852 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: 0.5329. Min Range: -0.5329

Max Act: 0.5249. Min Act: -0.0000

Data Index: 128558 (The Pile)

Max Activating Token Index: 113

Text #1

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.5329. Min Act: -0.0000

Data Index: 627040 (The Pile)

Max Activating Token Index: 331

Text #2

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.5200. Min Act: -0.0000

Data Index: 1787394 (The Pile)

Max Activating Token Index: 217

Text #3

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.4961. Min Act: -0.0000

Data Index: 615724 (The Pile)

Max Activating Token Index: 258

Text #4

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.4619. Min Act: -0.0000

Data Index: 1199381 (The Pile)

Max Activating Token Index: 687

Text #5

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.4446. Min Act: -0.0000

Data Index: 1353486 (The Pile)

Max Activating Token Index: 66

Text #6

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.4623. Min Act: -0.0000

Data Index: 944378 (The Pile)

Max Activating Token Index: 53

Text #7

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.4650. Min Act: -0.0000

Data Index: 713443 (The Pile)

Max Activating Token Index: 984

Text #8

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.4291. Min Act: -0.0000

Data Index: 638883 (The Pile)

Max Activating Token Index: 222

Text #9

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.4293. Min Act: -0.0000

Data Index: 775423 (The Pile)

Max Activating Token Index: 435

Text #10

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.4107. Min Act: -0.0000

Data Index: 832157 (The Pile)

Max Activating Token Index: 477

Text #11

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.4230. Min Act: -0.0000

Data Index: 347239 (The Pile)

Max Activating Token Index: 301

Text #12

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.4052. Min Act: -0.0000

Data Index: 1388882 (The Pile)

Max Activating Token Index: 161

Text #13

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.4164. Min Act: -0.0000

Data Index: 1426197 (The Pile)

Max Activating Token Index: 333

Text #14

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.4148. Min Act: -0.0000

Data Index: 1518540 (The Pile)

Max Activating Token Index: 998

Text #15

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.3824. Min Act: -0.0000

Data Index: 1419289 (The Pile)

Max Activating Token Index: 564

Text #16

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.4042. Min Act: -0.0000

Data Index: 476467 (The Pile)

Max Activating Token Index: 184

Text #17

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.3895. Min Act: -0.0000

Data Index: 1403196 (The Pile)

Max Activating Token Index: 365

Text #18

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.3867. Min Act: -0.0000

Data Index: 962506 (The Pile)

Max Activating Token Index: 241

Text #19

Max Range: 0.5329. Min Range: -0.5329

Max Act: 0.3767. Min Act: -0.0000

Data Index: 1734514 (The Pile)

Max Activating Token Index: 138