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

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

Neuron 4720 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: 0.1419. Min Range: -0.1419

Max Act: 0.1419. Min Act: -0.0001

Data Index: 401021 (C4 (Web Text))

Max Activating Token Index: 600

Text #1

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.1266. Min Act: -0.0001

Data Index: 1163254 (C4 (Web Text))

Max Activating Token Index: 259

Text #2

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.1092. Min Act: -0.0001

Data Index: 1186342 (C4 (Web Text))

Max Activating Token Index: 48

Text #3

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.1025. Min Act: -0.0001

Data Index: 204797 (C4 (Web Text))

Max Activating Token Index: 873

Text #4

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.0979. Min Act: -0.0001

Data Index: 230784 (C4 (Web Text))

Max Activating Token Index: 444

Text #5

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.0978. Min Act: -0.0001

Data Index: 715285 (C4 (Web Text))

Max Activating Token Index: 90

Text #6

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.0967. Min Act: -0.0001

Data Index: 1261912 (C4 (Web Text))

Max Activating Token Index: 805

Text #7

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.0959. Min Act: -0.0001

Data Index: 34354 (C4 (Web Text))

Max Activating Token Index: 146

Text #8

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.0886. Min Act: -0.0001

Data Index: 1194340 (C4 (Web Text))

Max Activating Token Index: 844

Text #9

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.0915. Min Act: -0.0001

Data Index: 1020392 (C4 (Web Text))

Max Activating Token Index: 312

Text #10

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.0899. Min Act: -0.0001

Data Index: 707884 (C4 (Web Text))

Max Activating Token Index: 913

Text #11

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.0862. Min Act: -0.0001

Data Index: 260552 (C4 (Web Text))

Max Activating Token Index: 19

Text #12

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.0739. Min Act: -0.0000

Data Index: 937158 (C4 (Web Text))

Max Activating Token Index: 272

Text #13

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.0812. Min Act: -0.0001

Data Index: 886876 (C4 (Web Text))

Max Activating Token Index: 458

Text #14

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.0723. Min Act: -0.0001

Data Index: 589624 (C4 (Web Text))

Max Activating Token Index: 594

Text #15

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.0695. Min Act: -0.0001

Data Index: 781460 (C4 (Web Text))

Max Activating Token Index: 47

Text #16

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.0714. Min Act: -0.0001

Data Index: 851109 (C4 (Web Text))

Max Activating Token Index: 173

Text #17

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.0654. Min Act: -0.0001

Data Index: 54446 (C4 (Web Text))

Max Activating Token Index: 109

Text #18

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.0688. Min Act: -0.0001

Data Index: 343088 (C4 (Web Text))

Max Activating Token Index: 64

Text #19

Max Range: 0.1419. Min Range: -0.1419

Max Act: 0.0650. Min Act: -0.0001

Data Index: 189839 (C4 (Web Text))

Max Activating Token Index: 916