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

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

Neuron 1224 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3252. Min Range: -1.3252

Max Act: 1.3252. Min Act: -0.0000

Data Index: 400113 (C4 (Web Text))

Max Activating Token Index: 531

Text #1

Max Range: 1.3252. Min Range: -1.3252

Max Act: 1.1408. Min Act: -0.0000

Data Index: 911403 (C4 (Web Text))

Max Activating Token Index: 622

Text #2

Max Range: 1.3252. Min Range: -1.3252

Max Act: 1.1580. Min Act: 0.0000

Data Index: 651242 (C4 (Web Text))

Max Activating Token Index: 950

Text #3

Max Range: 1.3252. Min Range: -1.3252

Max Act: 1.0634. Min Act: -0.0000

Data Index: 1191674 (C4 (Web Text))

Max Activating Token Index: 156

Text #4

Max Range: 1.3252. Min Range: -1.3252

Max Act: 1.0443. Min Act: -0.0000

Data Index: 1228673 (C4 (Web Text))

Max Activating Token Index: 477

Text #5

Max Range: 1.3252. Min Range: -1.3252

Max Act: 0.9939. Min Act: -0.0000

Data Index: 652015 (C4 (Web Text))

Max Activating Token Index: 462

Text #6

Max Range: 1.3252. Min Range: -1.3252

Max Act: 0.9384. Min Act: -0.0000

Data Index: 952761 (C4 (Web Text))

Max Activating Token Index: 616

Text #7

Max Range: 1.3252. Min Range: -1.3252

Max Act: 0.9847. Min Act: -0.0000

Data Index: 937793 (C4 (Web Text))

Max Activating Token Index: 51

Text #8

Max Range: 1.3252. Min Range: -1.3252

Max Act: 1.0379. Min Act: -0.0000

Data Index: 401578 (C4 (Web Text))

Max Activating Token Index: 995

Text #9

Max Range: 1.3252. Min Range: -1.3252

Max Act: 0.9697. Min Act: -0.0000

Data Index: 161592 (C4 (Web Text))

Max Activating Token Index: 668

Text #10

Max Range: 1.3252. Min Range: -1.3252

Max Act: 0.9025. Min Act: -0.0000

Data Index: 1332681 (C4 (Web Text))

Max Activating Token Index: 65

Text #11

Max Range: 1.3252. Min Range: -1.3252

Max Act: 0.9334. Min Act: -0.0000

Data Index: 1357332 (C4 (Web Text))

Max Activating Token Index: 391

Text #12

Max Range: 1.3252. Min Range: -1.3252

Max Act: 0.9065. Min Act: -0.0000

Data Index: 1107153 (C4 (Web Text))

Max Activating Token Index: 451

Text #13

Max Range: 1.3252. Min Range: -1.3252

Max Act: 0.9431. Min Act: -0.0000

Data Index: 1184791 (C4 (Web Text))

Max Activating Token Index: 277

Text #14

Max Range: 1.3252. Min Range: -1.3252

Max Act: 0.9654. Min Act: -0.0000

Data Index: 1192300 (C4 (Web Text))

Max Activating Token Index: 703

Text #15

Max Range: 1.3252. Min Range: -1.3252

Max Act: 0.9092. Min Act: -0.0000

Data Index: 1288810 (C4 (Web Text))

Max Activating Token Index: 460

Text #16

Max Range: 1.3252. Min Range: -1.3252

Max Act: 0.9013. Min Act: -0.0000

Data Index: 744107 (C4 (Web Text))

Max Activating Token Index: 517

Text #17

Max Range: 1.3252. Min Range: -1.3252

Max Act: 0.8725. Min Act: -0.0000

Data Index: 507733 (C4 (Web Text))

Max Activating Token Index: 213

Text #18

Max Range: 1.3252. Min Range: -1.3252

Max Act: 0.8021. Min Act: -0.0000

Data Index: 1280947 (C4 (Web Text))

Max Activating Token Index: 162

Text #19

Max Range: 1.3252. Min Range: -1.3252

Max Act: 0.8357. Min Act: -0.0000

Data Index: 319647 (C4 (Web Text))

Max Activating Token Index: 592