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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1051 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8986. Min Range: -1.8986

Max Act: 1.8216. Min Act: -0.0000

Data Index: 109909 (C4 (Web Text))

Max Activating Token Index: 906

Text #1

Max Range: 1.8986. Min Range: -1.8986

Max Act: 1.8986. Min Act: -0.0000

Data Index: 421595 (C4 (Web Text))

Max Activating Token Index: 838

Text #2

Max Range: 1.8986. Min Range: -1.8986

Max Act: 1.6042. Min Act: -0.0000

Data Index: 49560 (C4 (Web Text))

Max Activating Token Index: 483

Text #3

Max Range: 1.8986. Min Range: -1.8986

Max Act: 1.4473. Min Act: -0.0000

Data Index: 442346 (C4 (Web Text))

Max Activating Token Index: 603

Text #4

Max Range: 1.8986. Min Range: -1.8986

Max Act: 1.5139. Min Act: -0.0000

Data Index: 114765 (C4 (Web Text))

Max Activating Token Index: 556

Text #5

Max Range: 1.8986. Min Range: -1.8986

Max Act: 1.3638. Min Act: -0.0000

Data Index: 187181 (C4 (Web Text))

Max Activating Token Index: 798

Text #6

Max Range: 1.8986. Min Range: -1.8986

Max Act: 1.4317. Min Act: -0.0000

Data Index: 940700 (C4 (Web Text))

Max Activating Token Index: 65

Text #7

Max Range: 1.8986. Min Range: -1.8986

Max Act: 1.3859. Min Act: -0.0000

Data Index: 140998 (C4 (Web Text))

Max Activating Token Index: 539

Text #8

Max Range: 1.8986. Min Range: -1.8986

Max Act: 1.4267. Min Act: -0.0000

Data Index: 760358 (C4 (Web Text))

Max Activating Token Index: 90

Text #9

Max Range: 1.8986. Min Range: -1.8986

Max Act: 1.4132. Min Act: -0.0000

Data Index: 641304 (C4 (Web Text))

Max Activating Token Index: 141

Text #10

Max Range: 1.8986. Min Range: -1.8986

Max Act: 1.4307. Min Act: -0.0000

Data Index: 570763 (C4 (Web Text))

Max Activating Token Index: 956

Text #11

Max Range: 1.8986. Min Range: -1.8986

Max Act: 1.3468. Min Act: -0.0000

Data Index: 1013141 (C4 (Web Text))

Max Activating Token Index: 548

Text #12

Max Range: 1.8986. Min Range: -1.8986

Max Act: 1.2173. Min Act: -0.0000

Data Index: 101643 (C4 (Web Text))

Max Activating Token Index: 855

Text #13

Max Range: 1.8986. Min Range: -1.8986

Max Act: 1.3328. Min Act: -0.0000

Data Index: 473066 (C4 (Web Text))

Max Activating Token Index: 536

Text #14

Max Range: 1.8986. Min Range: -1.8986

Max Act: 1.2601. Min Act: -0.0000

Data Index: 537972 (C4 (Web Text))

Max Activating Token Index: 997

Text #15

Max Range: 1.8986. Min Range: -1.8986

Max Act: 1.2492. Min Act: -0.0000

Data Index: 384366 (C4 (Web Text))

Max Activating Token Index: 27

Text #16

Max Range: 1.8986. Min Range: -1.8986

Max Act: 1.2759. Min Act: -0.0000

Data Index: 451035 (C4 (Web Text))

Max Activating Token Index: 847

Text #17

Max Range: 1.8986. Min Range: -1.8986

Max Act: 1.2269. Min Act: -0.0000

Data Index: 1317883 (C4 (Web Text))

Max Activating Token Index: 603

Text #18

Max Range: 1.8986. Min Range: -1.8986

Max Act: 1.3114. Min Act: -0.0000

Data Index: 438781 (C4 (Web Text))

Max Activating Token Index: 837

Text #19

Max Range: 1.8986. Min Range: -1.8986

Max Act: 1.2668. Min Act: -0.0000

Data Index: 823596 (C4 (Web Text))

Max Activating Token Index: 677