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

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

Neuron 3140 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: 0.0613. Min Range: -0.0613

Max Act: 0.0613. Min Act: -0.0001

Data Index: 513116 (C4 (Web Text))

Max Activating Token Index: 823

Text #1

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0562. Min Act: -0.0001

Data Index: 409019 (C4 (Web Text))

Max Activating Token Index: 102

Text #2

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0524. Min Act: -0.0001

Data Index: 1064750 (C4 (Web Text))

Max Activating Token Index: 50

Text #3

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0527. Min Act: -0.0001

Data Index: 208716 (C4 (Web Text))

Max Activating Token Index: 116

Text #4

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0526. Min Act: -0.0001

Data Index: 15648 (C4 (Web Text))

Max Activating Token Index: 26

Text #5

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0515. Min Act: -0.0001

Data Index: 600587 (C4 (Web Text))

Max Activating Token Index: 104

Text #6

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0515. Min Act: -0.0001

Data Index: 71571 (C4 (Web Text))

Max Activating Token Index: 39

Text #7

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0502. Min Act: -0.0001

Data Index: 222039 (C4 (Web Text))

Max Activating Token Index: 371

Text #8

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0540. Min Act: -0.0001

Data Index: 187301 (C4 (Web Text))

Max Activating Token Index: 726

Text #9

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0510. Min Act: -0.0001

Data Index: 641897 (C4 (Web Text))

Max Activating Token Index: 24

Text #10

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0493. Min Act: -0.0001

Data Index: 629563 (C4 (Web Text))

Max Activating Token Index: 719

Text #11

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0476. Min Act: -0.0001

Data Index: 1499304 (Python Code)

Max Activating Token Index: 606

Text #12

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0471. Min Act: -0.0001

Data Index: 539966 (C4 (Web Text))

Max Activating Token Index: 195

Text #13

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0469. Min Act: -0.0001

Data Index: 1243059 (C4 (Web Text))

Max Activating Token Index: 32

Text #14

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0498. Min Act: -0.0001

Data Index: 790880 (C4 (Web Text))

Max Activating Token Index: 751

Text #15

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0395. Min Act: -0.0001

Data Index: 710255 (C4 (Web Text))

Max Activating Token Index: 202

Text #16

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0461. Min Act: -0.0001

Data Index: 465721 (C4 (Web Text))

Max Activating Token Index: 166

Text #17

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0452. Min Act: -0.0001

Data Index: 714552 (C4 (Web Text))

Max Activating Token Index: 28

Text #18

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0466. Min Act: -0.0001

Data Index: 751524 (C4 (Web Text))

Max Activating Token Index: 94

Text #19

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0474. Min Act: -0.0001

Data Index: 684627 (C4 (Web Text))

Max Activating Token Index: 283