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

Dataset: The Pile

Neuron 1071 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2091. Min Range: -3.2091

Max Act: 3.2091. Min Act: -0.0000

Data Index: 1628871 (The Pile)

Max Activating Token Index: 536

Text #1

Max Range: 3.2091. Min Range: -3.2091

Max Act: 3.1653. Min Act: -0.0000

Data Index: 1854696 (The Pile)

Max Activating Token Index: 91

Text #2

Max Range: 3.2091. Min Range: -3.2091

Max Act: 3.0328. Min Act: -0.0000

Data Index: 305161 (The Pile)

Max Activating Token Index: 352

Text #3

Max Range: 3.2091. Min Range: -3.2091

Max Act: 2.8692. Min Act: -0.0000

Data Index: 1183024 (The Pile)

Max Activating Token Index: 674

Text #4

Max Range: 3.2091. Min Range: -3.2091

Max Act: 3.0332. Min Act: -0.0000

Data Index: 234778 (The Pile)

Max Activating Token Index: 77

Text #5

Max Range: 3.2091. Min Range: -3.2091

Max Act: 2.8363. Min Act: -0.0000

Data Index: 425551 (The Pile)

Max Activating Token Index: 519

Text #6

Max Range: 3.2091. Min Range: -3.2091

Max Act: 3.0223. Min Act: -0.0000

Data Index: 1240483 (The Pile)

Max Activating Token Index: 603

Text #7

Max Range: 3.2091. Min Range: -3.2091

Max Act: 2.8606. Min Act: -0.0000

Data Index: 165782 (The Pile)

Max Activating Token Index: 544

Text #8

Max Range: 3.2091. Min Range: -3.2091

Max Act: 2.6725. Min Act: -0.0000

Data Index: 812516 (The Pile)

Max Activating Token Index: 162

Text #9

Max Range: 3.2091. Min Range: -3.2091

Max Act: 2.6220. Min Act: -0.0000

Data Index: 1909971 (The Pile)

Max Activating Token Index: 150

Text #10

Max Range: 3.2091. Min Range: -3.2091

Max Act: 2.8222. Min Act: -0.0000

Data Index: 807298 (The Pile)

Max Activating Token Index: 501

Text #11

Max Range: 3.2091. Min Range: -3.2091

Max Act: 2.5475. Min Act: -0.0000

Data Index: 87866 (The Pile)

Max Activating Token Index: 988

Text #12

Max Range: 3.2091. Min Range: -3.2091

Max Act: 2.5402. Min Act: -0.0000

Data Index: 202530 (The Pile)

Max Activating Token Index: 210

Text #13

Max Range: 3.2091. Min Range: -3.2091

Max Act: 2.2734. Min Act: -0.0000

Data Index: 1207692 (The Pile)

Max Activating Token Index: 335

Text #14

Max Range: 3.2091. Min Range: -3.2091

Max Act: 2.5352. Min Act: -0.0000

Data Index: 779628 (The Pile)

Max Activating Token Index: 369

Text #15

Max Range: 3.2091. Min Range: -3.2091

Max Act: 2.6316. Min Act: -0.0000

Data Index: 1360652 (The Pile)

Max Activating Token Index: 860

Text #16

Max Range: 3.2091. Min Range: -3.2091

Max Act: 2.3807. Min Act: -0.0000

Data Index: 491853 (The Pile)

Max Activating Token Index: 829

Text #17

Max Range: 3.2091. Min Range: -3.2091

Max Act: 2.6056. Min Act: -0.0000

Data Index: 1530941 (The Pile)

Max Activating Token Index: 668

Text #18

Max Range: 3.2091. Min Range: -3.2091

Max Act: 2.3517. Min Act: -0.0000

Data Index: 1584854 (The Pile)

Max Activating Token Index: 276

Text #19

Max Range: 3.2091. Min Range: -3.2091

Max Act: 2.6151. Min Act: -0.0000

Data Index: 1812496 (The Pile)

Max Activating Token Index: 804