Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5108 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.2414. Min Act: -0.0001

Data Index: 736931 (C4 (Web Text))

Max Activating Token Index: 143

Text #1

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.2223. Min Act: -0.0001

Data Index: 261762 (C4 (Web Text))

Max Activating Token Index: 988

Text #2

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.2027. Min Act: -0.0001

Data Index: 679273 (C4 (Web Text))

Max Activating Token Index: 295

Text #3

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.1728. Min Act: -0.0001

Data Index: 667084 (C4 (Web Text))

Max Activating Token Index: 969

Text #4

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.1745. Min Act: -0.0001

Data Index: 778515 (C4 (Web Text))

Max Activating Token Index: 371

Text #5

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.1772. Min Act: -0.0001

Data Index: 976736 (C4 (Web Text))

Max Activating Token Index: 968

Text #6

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.1642. Min Act: -0.0001

Data Index: 706971 (C4 (Web Text))

Max Activating Token Index: 1011

Text #7

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.1673. Min Act: -0.0001

Data Index: 712776 (C4 (Web Text))

Max Activating Token Index: 596

Text #8

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.1613. Min Act: -0.0001

Data Index: 759531 (C4 (Web Text))

Max Activating Token Index: 292

Text #9

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.1593. Min Act: -0.0001

Data Index: 864796 (C4 (Web Text))

Max Activating Token Index: 188

Text #10

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.1391. Min Act: -0.0001

Data Index: 964881 (C4 (Web Text))

Max Activating Token Index: 1000

Text #11

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.1523. Min Act: -0.0001

Data Index: 219432 (C4 (Web Text))

Max Activating Token Index: 104

Text #12

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.1509. Min Act: -0.0001

Data Index: 613960 (C4 (Web Text))

Max Activating Token Index: 191

Text #13

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.1413. Min Act: -0.0001

Data Index: 1026339 (C4 (Web Text))

Max Activating Token Index: 298

Text #14

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.1523. Min Act: -0.0001

Data Index: 356042 (C4 (Web Text))

Max Activating Token Index: 497

Text #15

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.1654. Min Act: -0.0001

Data Index: 545340 (C4 (Web Text))

Max Activating Token Index: 691

Text #16

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.1580. Min Act: -0.0001

Data Index: 1175715 (C4 (Web Text))

Max Activating Token Index: 850

Text #17

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.1481. Min Act: -0.0001

Data Index: 399991 (C4 (Web Text))

Max Activating Token Index: 655

Text #18

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.1609. Min Act: -0.0000

Data Index: 242156 (C4 (Web Text))

Max Activating Token Index: 316

Text #19

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.1512. Min Act: -0.0001

Data Index: 243700 (C4 (Web Text))

Max Activating Token Index: 31