Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3957 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3221. Min Range: -1.3221

Max Act: 1.3221. Min Act: -0.0001

Data Index: 203442 (C4 (Web Text))

Max Activating Token Index: 31

Text #1

Max Range: 1.3221. Min Range: -1.3221

Max Act: 1.1987. Min Act: -0.0001

Data Index: 906761 (C4 (Web Text))

Max Activating Token Index: 64

Text #2

Max Range: 1.3221. Min Range: -1.3221

Max Act: 1.2344. Min Act: -0.0001

Data Index: 136765 (C4 (Web Text))

Max Activating Token Index: 276

Text #3

Max Range: 1.3221. Min Range: -1.3221

Max Act: 1.2227. Min Act: -0.0001

Data Index: 398875 (C4 (Web Text))

Max Activating Token Index: 80

Text #4

Max Range: 1.3221. Min Range: -1.3221

Max Act: 1.1785. Min Act: -0.0001

Data Index: 553057 (C4 (Web Text))

Max Activating Token Index: 879

Text #5

Max Range: 1.3221. Min Range: -1.3221

Max Act: 1.1819. Min Act: -0.0001

Data Index: 986629 (C4 (Web Text))

Max Activating Token Index: 930

Text #6

Max Range: 1.3221. Min Range: -1.3221

Max Act: 1.1729. Min Act: -0.0001

Data Index: 243008 (C4 (Web Text))

Max Activating Token Index: 69

Text #7

Max Range: 1.3221. Min Range: -1.3221

Max Act: 1.1322. Min Act: -0.0001

Data Index: 658562 (C4 (Web Text))

Max Activating Token Index: 605

Text #8

Max Range: 1.3221. Min Range: -1.3221

Max Act: 1.0577. Min Act: -0.0001

Data Index: 338559 (C4 (Web Text))

Max Activating Token Index: 790

Text #9

Max Range: 1.3221. Min Range: -1.3221

Max Act: 1.1124. Min Act: -0.0001

Data Index: 58421 (C4 (Web Text))

Max Activating Token Index: 996

Text #10

Max Range: 1.3221. Min Range: -1.3221

Max Act: 1.1013. Min Act: -0.0001

Data Index: 477577 (C4 (Web Text))

Max Activating Token Index: 170

Text #11

Max Range: 1.3221. Min Range: -1.3221

Max Act: 1.1325. Min Act: -0.0001

Data Index: 119494 (C4 (Web Text))

Max Activating Token Index: 990

Text #12

Max Range: 1.3221. Min Range: -1.3221

Max Act: 1.0678. Min Act: -0.0001

Data Index: 1236282 (C4 (Web Text))

Max Activating Token Index: 384

Text #13

Max Range: 1.3221. Min Range: -1.3221

Max Act: 1.0691. Min Act: -0.0001

Data Index: 1128757 (C4 (Web Text))

Max Activating Token Index: 186

Text #14

Max Range: 1.3221. Min Range: -1.3221

Max Act: 1.0835. Min Act: -0.0001

Data Index: 1228914 (C4 (Web Text))

Max Activating Token Index: 80

Text #15

Max Range: 1.3221. Min Range: -1.3221

Max Act: 1.0864. Min Act: -0.0001

Data Index: 834496 (C4 (Web Text))

Max Activating Token Index: 806

Text #16

Max Range: 1.3221. Min Range: -1.3221

Max Act: 1.0818. Min Act: -0.0001

Data Index: 56229 (C4 (Web Text))

Max Activating Token Index: 290

Text #17

Max Range: 1.3221. Min Range: -1.3221

Max Act: 1.0969. Min Act: -0.0001

Data Index: 39900 (C4 (Web Text))

Max Activating Token Index: 751

Text #18

Max Range: 1.3221. Min Range: -1.3221

Max Act: 1.0343. Min Act: -0.0001

Data Index: 501249 (C4 (Web Text))

Max Activating Token Index: 970

Text #19

Max Range: 1.3221. Min Range: -1.3221

Max Act: 1.0409. Min Act: -0.0001

Data Index: 938623 (C4 (Web Text))

Max Activating Token Index: 225