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

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

Neuron 792 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0575. Min Act: -0.0001

Data Index: 1064595 (C4 (Web Text))

Max Activating Token Index: 98

Text #1

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0593. Min Act: -0.0001

Data Index: 636466 (C4 (Web Text))

Max Activating Token Index: 347

Text #2

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0594. Min Act: -0.0001

Data Index: 356806 (C4 (Web Text))

Max Activating Token Index: 264

Text #3

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0531. Min Act: -0.0002

Data Index: 341979 (C4 (Web Text))

Max Activating Token Index: 608

Text #4

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0555. Min Act: -0.0001

Data Index: 539942 (C4 (Web Text))

Max Activating Token Index: 108

Text #5

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0514. Min Act: -0.0001

Data Index: 1260333 (C4 (Web Text))

Max Activating Token Index: 997

Text #6

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0527. Min Act: -0.0001

Data Index: 946094 (C4 (Web Text))

Max Activating Token Index: 58

Text #7

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0523. Min Act: -0.0001

Data Index: 1210862 (C4 (Web Text))

Max Activating Token Index: 559

Text #8

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0520. Min Act: -0.0001

Data Index: 895234 (C4 (Web Text))

Max Activating Token Index: 298

Text #9

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0537. Min Act: -0.0002

Data Index: 120887 (C4 (Web Text))

Max Activating Token Index: 266

Text #10

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0516. Min Act: -0.0001

Data Index: 1009342 (C4 (Web Text))

Max Activating Token Index: 69

Text #11

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0495. Min Act: -0.0001

Data Index: 153023 (C4 (Web Text))

Max Activating Token Index: 79

Text #12

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0553. Min Act: -0.0001

Data Index: 643661 (C4 (Web Text))

Max Activating Token Index: 872

Text #13

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0532. Min Act: -0.0001

Data Index: 589966 (C4 (Web Text))

Max Activating Token Index: 50

Text #14

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0527. Min Act: -0.0001

Data Index: 1353960 (C4 (Web Text))

Max Activating Token Index: 446

Text #15

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0505. Min Act: -0.0001

Data Index: 675531 (C4 (Web Text))

Max Activating Token Index: 145

Text #16

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0501. Min Act: -0.0001

Data Index: 134305 (C4 (Web Text))

Max Activating Token Index: 626

Text #17

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0507. Min Act: -0.0002

Data Index: 1303643 (C4 (Web Text))

Max Activating Token Index: 502

Text #18

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0512. Min Act: -0.0001

Data Index: 1231834 (C4 (Web Text))

Max Activating Token Index: 356

Text #19

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0493. Min Act: -0.0001

Data Index: 455429 (C4 (Web Text))

Max Activating Token Index: 389