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

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

Neuron 1046 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0930. Min Act: -0.0001

Data Index: 1608615 (Python Code)

Max Activating Token Index: 604

Text #1

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0696. Min Act: -0.0001

Data Index: 1523498 (Python Code)

Max Activating Token Index: 170

Text #2

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0606. Min Act: -0.0000

Data Index: 924019 (C4 (Web Text))

Max Activating Token Index: 372

Text #3

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0557. Min Act: -0.0000

Data Index: 280153 (C4 (Web Text))

Max Activating Token Index: 96

Text #4

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0620. Min Act: -0.0000

Data Index: 267438 (C4 (Web Text))

Max Activating Token Index: 125

Text #5

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0581. Min Act: -0.0000

Data Index: 901116 (C4 (Web Text))

Max Activating Token Index: 355

Text #6

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0546. Min Act: -0.0000

Data Index: 529661 (C4 (Web Text))

Max Activating Token Index: 991

Text #7

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0592. Min Act: -0.0000

Data Index: 652866 (C4 (Web Text))

Max Activating Token Index: 234

Text #8

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0536. Min Act: -0.0000

Data Index: 638963 (C4 (Web Text))

Max Activating Token Index: 961

Text #9

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0534. Min Act: -0.0000

Data Index: 1309639 (C4 (Web Text))

Max Activating Token Index: 237

Text #10

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0573. Min Act: -0.0001

Data Index: 1503273 (Python Code)

Max Activating Token Index: 1006

Text #11

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0569. Min Act: -0.0000

Data Index: 183012 (C4 (Web Text))

Max Activating Token Index: 765

Text #12

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0528. Min Act: -0.0000

Data Index: 688885 (C4 (Web Text))

Max Activating Token Index: 983

Text #13

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0541. Min Act: -0.0000

Data Index: 123953 (C4 (Web Text))

Max Activating Token Index: 151

Text #14

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0541. Min Act: -0.0000

Data Index: 348083 (C4 (Web Text))

Max Activating Token Index: 492

Text #15

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0555. Min Act: -0.0000

Data Index: 384730 (C4 (Web Text))

Max Activating Token Index: 837

Text #16

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0526. Min Act: -0.0001

Data Index: 716368 (C4 (Web Text))

Max Activating Token Index: 156

Text #17

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0500. Min Act: -0.0000

Data Index: 1294729 (C4 (Web Text))

Max Activating Token Index: 771

Text #18

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0527. Min Act: -0.0000

Data Index: 628643 (C4 (Web Text))

Max Activating Token Index: 969

Text #19

Max Range: 0.0930. Min Range: -0.0930

Max Act: 0.0508. Min Act: -0.0001

Data Index: 1033288 (C4 (Web Text))

Max Activating Token Index: 555