Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 892 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0705. Min Act: -0.0003

Data Index: 736971 (C4 (Web Text))

Max Activating Token Index: 76

Text #1

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0610. Min Act: -0.0004

Data Index: 94171 (C4 (Web Text))

Max Activating Token Index: 899

Text #2

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0603. Min Act: -0.0003

Data Index: 601572 (C4 (Web Text))

Max Activating Token Index: 779

Text #3

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0616. Min Act: -0.0003

Data Index: 733582 (C4 (Web Text))

Max Activating Token Index: 192

Text #4

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0628. Min Act: -0.0003

Data Index: 345769 (C4 (Web Text))

Max Activating Token Index: 716

Text #5

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0605. Min Act: -0.0003

Data Index: 925062 (C4 (Web Text))

Max Activating Token Index: 21

Text #6

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0590. Min Act: -0.0003

Data Index: 535366 (C4 (Web Text))

Max Activating Token Index: 1004

Text #7

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0594. Min Act: -0.0004

Data Index: 538299 (C4 (Web Text))

Max Activating Token Index: 835

Text #8

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0583. Min Act: -0.0003

Data Index: 1139061 (C4 (Web Text))

Max Activating Token Index: 691

Text #9

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0609. Min Act: -0.0003

Data Index: 762733 (C4 (Web Text))

Max Activating Token Index: 420

Text #10

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0614. Min Act: -0.0003

Data Index: 868083 (C4 (Web Text))

Max Activating Token Index: 171

Text #11

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0573. Min Act: -0.0004

Data Index: 894519 (C4 (Web Text))

Max Activating Token Index: 1002

Text #12

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0583. Min Act: -0.0003

Data Index: 835888 (C4 (Web Text))

Max Activating Token Index: 421

Text #13

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0555. Min Act: -0.0004

Data Index: 989966 (C4 (Web Text))

Max Activating Token Index: 552

Text #14

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0570. Min Act: -0.0003

Data Index: 183936 (C4 (Web Text))

Max Activating Token Index: 75

Text #15

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0559. Min Act: -0.0003

Data Index: 1098080 (C4 (Web Text))

Max Activating Token Index: 855

Text #16

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0558. Min Act: -0.0003

Data Index: 366968 (C4 (Web Text))

Max Activating Token Index: 565

Text #17

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0572. Min Act: -0.0004

Data Index: 788001 (C4 (Web Text))

Max Activating Token Index: 589

Text #18

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0557. Min Act: -0.0004

Data Index: 472599 (C4 (Web Text))

Max Activating Token Index: 155

Text #19

Max Range: 0.0705. Min Range: -0.0705

Max Act: 0.0563. Min Act: -0.0003

Data Index: 1306921 (C4 (Web Text))

Max Activating Token Index: 944