Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1721 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7838. Min Range: -0.7838

Max Act: 0.7786. Min Act: -0.0000

Data Index: 526880 (C4 (Web Text))

Max Activating Token Index: 249

Text #1

Max Range: 0.7838. Min Range: -0.7838

Max Act: 0.7838. Min Act: -0.0001

Data Index: 29334 (C4 (Web Text))

Max Activating Token Index: 228

Text #2

Max Range: 0.7838. Min Range: -0.7838

Max Act: 0.7493. Min Act: -0.0000

Data Index: 317809 (C4 (Web Text))

Max Activating Token Index: 777

Text #3

Max Range: 0.7838. Min Range: -0.7838

Max Act: 0.6591. Min Act: -0.0000

Data Index: 376300 (C4 (Web Text))

Max Activating Token Index: 932

Text #4

Max Range: 0.7838. Min Range: -0.7838

Max Act: 0.6915. Min Act: -0.0001

Data Index: 1319492 (C4 (Web Text))

Max Activating Token Index: 478

Text #5

Max Range: 0.7838. Min Range: -0.7838

Max Act: 0.7145. Min Act: -0.0001

Data Index: 418798 (C4 (Web Text))

Max Activating Token Index: 807

Text #6

Max Range: 0.7838. Min Range: -0.7838

Max Act: 0.6282. Min Act: -0.0000

Data Index: 580405 (C4 (Web Text))

Max Activating Token Index: 611

Text #7

Max Range: 0.7838. Min Range: -0.7838

Max Act: 0.7004. Min Act: -0.0001

Data Index: 46794 (C4 (Web Text))

Max Activating Token Index: 805

Text #8

Max Range: 0.7838. Min Range: -0.7838

Max Act: 0.6560. Min Act: -0.0000

Data Index: 1244594 (C4 (Web Text))

Max Activating Token Index: 239

Text #9

Max Range: 0.7838. Min Range: -0.7838

Max Act: 0.6363. Min Act: -0.0000

Data Index: 1212398 (C4 (Web Text))

Max Activating Token Index: 582

Text #10

Max Range: 0.7838. Min Range: -0.7838

Max Act: 0.6099. Min Act: -0.0000

Data Index: 340653 (C4 (Web Text))

Max Activating Token Index: 19

Text #11

Max Range: 0.7838. Min Range: -0.7838

Max Act: 0.6572. Min Act: -0.0000

Data Index: 956938 (C4 (Web Text))

Max Activating Token Index: 126

Text #12

Max Range: 0.7838. Min Range: -0.7838

Max Act: 0.6513. Min Act: -0.0000

Data Index: 425801 (C4 (Web Text))

Max Activating Token Index: 24

Text #13

Max Range: 0.7838. Min Range: -0.7838

Max Act: 0.6845. Min Act: -0.0000

Data Index: 727879 (C4 (Web Text))

Max Activating Token Index: 57

Text #14

Max Range: 0.7838. Min Range: -0.7838

Max Act: 0.6742. Min Act: -0.0000

Data Index: 1034969 (C4 (Web Text))

Max Activating Token Index: 967

Text #15

Max Range: 0.7838. Min Range: -0.7838

Max Act: 0.6198. Min Act: -0.0001

Data Index: 4397 (C4 (Web Text))

Max Activating Token Index: 445

Text #16

Max Range: 0.7838. Min Range: -0.7838

Max Act: 0.5787. Min Act: -0.0000

Data Index: 668588 (C4 (Web Text))

Max Activating Token Index: 230

Text #17

Max Range: 0.7838. Min Range: -0.7838

Max Act: 0.6589. Min Act: -0.0000

Data Index: 759919 (C4 (Web Text))

Max Activating Token Index: 500

Text #18

Max Range: 0.7838. Min Range: -0.7838

Max Act: 0.6153. Min Act: -0.0001

Data Index: 1169554 (C4 (Web Text))

Max Activating Token Index: 758

Text #19

Max Range: 0.7838. Min Range: -0.7838

Max Act: 0.5391. Min Act: -0.0000

Data Index: 1316612 (C4 (Web Text))

Max Activating Token Index: 150