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

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

Neuron 3696 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2962. Min Range: -1.2962

Max Act: 1.2889. Min Act: -0.0001

Data Index: 954436 (C4 (Web Text))

Max Activating Token Index: 415

Text #1

Max Range: 1.2962. Min Range: -1.2962

Max Act: 1.2962. Min Act: -0.0001

Data Index: 1291563 (C4 (Web Text))

Max Activating Token Index: 814

Text #2

Max Range: 1.2962. Min Range: -1.2962

Max Act: 1.2135. Min Act: -0.0001

Data Index: 748328 (C4 (Web Text))

Max Activating Token Index: 925

Text #3

Max Range: 1.2962. Min Range: -1.2962

Max Act: 1.2122. Min Act: -0.0001

Data Index: 201496 (C4 (Web Text))

Max Activating Token Index: 361

Text #4

Max Range: 1.2962. Min Range: -1.2962

Max Act: 1.2083. Min Act: -0.0001

Data Index: 202881 (C4 (Web Text))

Max Activating Token Index: 102

Text #5

Max Range: 1.2962. Min Range: -1.2962

Max Act: 1.1617. Min Act: -0.0001

Data Index: 587655 (C4 (Web Text))

Max Activating Token Index: 834

Text #6

Max Range: 1.2962. Min Range: -1.2962

Max Act: 1.1868. Min Act: -0.0001

Data Index: 907807 (C4 (Web Text))

Max Activating Token Index: 725

Text #7

Max Range: 1.2962. Min Range: -1.2962

Max Act: 1.1806. Min Act: -0.0001

Data Index: 570746 (C4 (Web Text))

Max Activating Token Index: 29

Text #8

Max Range: 1.2962. Min Range: -1.2962

Max Act: 1.1826. Min Act: -0.0001

Data Index: 1330970 (C4 (Web Text))

Max Activating Token Index: 401

Text #9

Max Range: 1.2962. Min Range: -1.2962

Max Act: 1.1816. Min Act: -0.0001

Data Index: 543668 (C4 (Web Text))

Max Activating Token Index: 279

Text #10

Max Range: 1.2962. Min Range: -1.2962

Max Act: 1.1428. Min Act: -0.0000

Data Index: 1037460 (C4 (Web Text))

Max Activating Token Index: 979

Text #11

Max Range: 1.2962. Min Range: -1.2962

Max Act: 1.1320. Min Act: -0.0001

Data Index: 1141046 (C4 (Web Text))

Max Activating Token Index: 37

Text #12

Max Range: 1.2962. Min Range: -1.2962

Max Act: 1.0989. Min Act: -0.0001

Data Index: 1011425 (C4 (Web Text))

Max Activating Token Index: 453

Text #13

Max Range: 1.2962. Min Range: -1.2962

Max Act: 1.0934. Min Act: -0.0001

Data Index: 11618 (C4 (Web Text))

Max Activating Token Index: 996

Text #14

Max Range: 1.2962. Min Range: -1.2962

Max Act: 1.1149. Min Act: -0.0001

Data Index: 148830 (C4 (Web Text))

Max Activating Token Index: 566

Text #15

Max Range: 1.2962. Min Range: -1.2962

Max Act: 1.0726. Min Act: -0.0001

Data Index: 79084 (C4 (Web Text))

Max Activating Token Index: 460

Text #16

Max Range: 1.2962. Min Range: -1.2962

Max Act: 1.0320. Min Act: -0.0001

Data Index: 2458 (C4 (Web Text))

Max Activating Token Index: 528

Text #17

Max Range: 1.2962. Min Range: -1.2962

Max Act: 1.0306. Min Act: -0.0001

Data Index: 822693 (C4 (Web Text))

Max Activating Token Index: 933

Text #18

Max Range: 1.2962. Min Range: -1.2962

Max Act: 1.0470. Min Act: -0.0001

Data Index: 292628 (C4 (Web Text))

Max Activating Token Index: 667

Text #19

Max Range: 1.2962. Min Range: -1.2962

Max Act: 1.0606. Min Act: -0.0001

Data Index: 1189683 (C4 (Web Text))

Max Activating Token Index: 218