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

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

Neuron 1165 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4038. Min Range: -1.4038

Max Act: 1.4038. Min Act: -0.0000

Data Index: 108840 (C4 (Web Text))

Max Activating Token Index: 326

Text #1

Max Range: 1.4038. Min Range: -1.4038

Max Act: 1.2919. Min Act: -0.0000

Data Index: 1000257 (C4 (Web Text))

Max Activating Token Index: 721

Text #2

Max Range: 1.4038. Min Range: -1.4038

Max Act: 1.2610. Min Act: -0.0000

Data Index: 996551 (C4 (Web Text))

Max Activating Token Index: 178

Text #3

Max Range: 1.4038. Min Range: -1.4038

Max Act: 1.3031. Min Act: -0.0000

Data Index: 11361 (C4 (Web Text))

Max Activating Token Index: 59

Text #4

Max Range: 1.4038. Min Range: -1.4038

Max Act: 1.1328. Min Act: -0.0000

Data Index: 93709 (C4 (Web Text))

Max Activating Token Index: 78

Text #5

Max Range: 1.4038. Min Range: -1.4038

Max Act: 1.1302. Min Act: -0.0000

Data Index: 711321 (C4 (Web Text))

Max Activating Token Index: 44

Text #6

Max Range: 1.4038. Min Range: -1.4038

Max Act: 1.1260. Min Act: -0.0000

Data Index: 204905 (C4 (Web Text))

Max Activating Token Index: 25

Text #7

Max Range: 1.4038. Min Range: -1.4038

Max Act: 1.0872. Min Act: -0.0000

Data Index: 347516 (C4 (Web Text))

Max Activating Token Index: 36

Text #8

Max Range: 1.4038. Min Range: -1.4038

Max Act: 1.1401. Min Act: -0.0000

Data Index: 686588 (C4 (Web Text))

Max Activating Token Index: 58

Text #9

Max Range: 1.4038. Min Range: -1.4038

Max Act: 1.1089. Min Act: -0.0000

Data Index: 23472 (C4 (Web Text))

Max Activating Token Index: 353

Text #10

Max Range: 1.4038. Min Range: -1.4038

Max Act: 1.0948. Min Act: -0.0000

Data Index: 1165096 (C4 (Web Text))

Max Activating Token Index: 6

Text #11

Max Range: 1.4038. Min Range: -1.4038

Max Act: 1.1257. Min Act: -0.0000

Data Index: 165200 (C4 (Web Text))

Max Activating Token Index: 11

Text #12

Max Range: 1.4038. Min Range: -1.4038

Max Act: 1.1244. Min Act: -0.0000

Data Index: 533763 (C4 (Web Text))

Max Activating Token Index: 758

Text #13

Max Range: 1.4038. Min Range: -1.4038

Max Act: 1.1129. Min Act: -0.0000

Data Index: 368586 (C4 (Web Text))

Max Activating Token Index: 1021

Text #14

Max Range: 1.4038. Min Range: -1.4038

Max Act: 1.0656. Min Act: -0.0000

Data Index: 260685 (C4 (Web Text))

Max Activating Token Index: 827

Text #15

Max Range: 1.4038. Min Range: -1.4038

Max Act: 1.0814. Min Act: -0.0000

Data Index: 786771 (C4 (Web Text))

Max Activating Token Index: 52

Text #16

Max Range: 1.4038. Min Range: -1.4038

Max Act: 1.0502. Min Act: -0.0000

Data Index: 195206 (C4 (Web Text))

Max Activating Token Index: 572

Text #17

Max Range: 1.4038. Min Range: -1.4038

Max Act: 1.0451. Min Act: -0.0000

Data Index: 1218679 (C4 (Web Text))

Max Activating Token Index: 30

Text #18

Max Range: 1.4038. Min Range: -1.4038

Max Act: 1.0436. Min Act: -0.0000

Data Index: 1208373 (C4 (Web Text))

Max Activating Token Index: 52

Text #19

Max Range: 1.4038. Min Range: -1.4038

Max Act: 1.0445. Min Act: -0.0000

Data Index: 581520 (C4 (Web Text))

Max Activating Token Index: 16