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

Dataset: The Pile

Neuron 1312 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.9096. Min Act: -0.0000

Data Index: 494259 (The Pile)

Max Activating Token Index: 808

Text #1

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.8459. Min Act: -0.0000

Data Index: 495142 (The Pile)

Max Activating Token Index: 669

Text #2

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.8253. Min Act: -0.0000

Data Index: 797654 (The Pile)

Max Activating Token Index: 611

Text #3

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.7746. Min Act: -0.0000

Data Index: 78312 (The Pile)

Max Activating Token Index: 589

Text #4

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.7273. Min Act: -0.0000

Data Index: 1240063 (The Pile)

Max Activating Token Index: 455

Text #5

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.6633. Min Act: -0.0000

Data Index: 1784580 (The Pile)

Max Activating Token Index: 806

Text #6

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.6672. Min Act: 0.0000

Data Index: 1848296 (The Pile)

Max Activating Token Index: 656

Text #7

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.6580. Min Act: -0.0000

Data Index: 158653 (The Pile)

Max Activating Token Index: 161

Text #8

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.6875. Min Act: -0.0000

Data Index: 137287 (The Pile)

Max Activating Token Index: 336

Text #9

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.6513. Min Act: -0.0000

Data Index: 1314075 (The Pile)

Max Activating Token Index: 411

Text #10

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.6747. Min Act: -0.0000

Data Index: 887275 (The Pile)

Max Activating Token Index: 956

Text #11

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.7050. Min Act: -0.0000

Data Index: 322276 (The Pile)

Max Activating Token Index: 569

Text #12

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.6407. Min Act: -0.0000

Data Index: 551011 (The Pile)

Max Activating Token Index: 505

Text #13

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.6606. Min Act: -0.0000

Data Index: 727392 (The Pile)

Max Activating Token Index: 962

Text #14

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.6808. Min Act: -0.0000

Data Index: 1715451 (The Pile)

Max Activating Token Index: 989

Text #15

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.6192. Min Act: -0.0000

Data Index: 1450215 (The Pile)

Max Activating Token Index: 538

Text #16

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.6582. Min Act: -0.0000

Data Index: 1985599 (The Pile)

Max Activating Token Index: 874

Text #17

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.6384. Min Act: -0.0000

Data Index: 1107190 (The Pile)

Max Activating Token Index: 210

Text #18

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.6518. Min Act: -0.0000

Data Index: 58092 (The Pile)

Max Activating Token Index: 726

Text #19

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.6355. Min Act: 0.0002

Data Index: 576533 (The Pile)

Max Activating Token Index: 678