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

Dataset: The Pile

Neuron 391 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: 1.3032. Min Range: -1.3032

Max Act: 1.3032. Min Act: -0.0000

Data Index: 538579 (The Pile)

Max Activating Token Index: 806

Text #1

Max Range: 1.3032. Min Range: -1.3032

Max Act: 0.7810. Min Act: -0.0000

Data Index: 485211 (The Pile)

Max Activating Token Index: 673

Text #2

Max Range: 1.3032. Min Range: -1.3032

Max Act: 0.6336. Min Act: -0.0000

Data Index: 145014 (The Pile)

Max Activating Token Index: 748

Text #3

Max Range: 1.3032. Min Range: -1.3032

Max Act: 0.5860. Min Act: -0.0000

Data Index: 398128 (The Pile)

Max Activating Token Index: 1002

Text #4

Max Range: 1.3032. Min Range: -1.3032

Max Act: 0.7015. Min Act: -0.0000

Data Index: 712682 (The Pile)

Max Activating Token Index: 797

Text #5

Max Range: 1.3032. Min Range: -1.3032

Max Act: 0.6079. Min Act: -0.0000

Data Index: 524095 (The Pile)

Max Activating Token Index: 878

Text #6

Max Range: 1.3032. Min Range: -1.3032

Max Act: 0.5984. Min Act: -0.0000

Data Index: 218666 (The Pile)

Max Activating Token Index: 483

Text #7

Max Range: 1.3032. Min Range: -1.3032

Max Act: 0.5802. Min Act: -0.0000

Data Index: 1835544 (The Pile)

Max Activating Token Index: 800

Text #8

Max Range: 1.3032. Min Range: -1.3032

Max Act: 0.6150. Min Act: -0.0000

Data Index: 588631 (The Pile)

Max Activating Token Index: 747

Text #9

Max Range: 1.3032. Min Range: -1.3032

Max Act: 0.5172. Min Act: -0.0000

Data Index: 1346374 (The Pile)

Max Activating Token Index: 1021

Text #10

Max Range: 1.3032. Min Range: -1.3032

Max Act: 0.5209. Min Act: -0.0000

Data Index: 1653796 (The Pile)

Max Activating Token Index: 553

Text #11

Max Range: 1.3032. Min Range: -1.3032

Max Act: 0.5628. Min Act: -0.0000

Data Index: 283052 (The Pile)

Max Activating Token Index: 484

Text #12

Max Range: 1.3032. Min Range: -1.3032

Max Act: 0.4552. Min Act: -0.0000

Data Index: 118236 (The Pile)

Max Activating Token Index: 156

Text #13

Max Range: 1.3032. Min Range: -1.3032

Max Act: 0.5039. Min Act: -0.0000

Data Index: 325270 (The Pile)

Max Activating Token Index: 861

Text #14

Max Range: 1.3032. Min Range: -1.3032

Max Act: 0.5135. Min Act: -0.0000

Data Index: 1492676 (The Pile)

Max Activating Token Index: 208

Text #15

Max Range: 1.3032. Min Range: -1.3032

Max Act: 0.5242. Min Act: -0.0000

Data Index: 934611 (The Pile)

Max Activating Token Index: 557

Text #16

Max Range: 1.3032. Min Range: -1.3032

Max Act: 0.5054. Min Act: -0.0000

Data Index: 1306196 (The Pile)

Max Activating Token Index: 662

Text #17

Max Range: 1.3032. Min Range: -1.3032

Max Act: 0.5462. Min Act: -0.0000

Data Index: 1634098 (The Pile)

Max Activating Token Index: 447

Text #18

Max Range: 1.3032. Min Range: -1.3032

Max Act: 0.4618. Min Act: -0.0000

Data Index: 977498 (The Pile)

Max Activating Token Index: 792

Text #19

Max Range: 1.3032. Min Range: -1.3032

Max Act: 0.5102. Min Act: -0.0000

Data Index: 22567 (The Pile)

Max Activating Token Index: 846