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

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

Neuron 4682 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2935. Min Range: -1.2935

Max Act: 1.2610. Min Act: -0.0001

Data Index: 1129472 (C4 (Web Text))

Max Activating Token Index: 63

Text #1

Max Range: 1.2935. Min Range: -1.2935

Max Act: 1.2935. Min Act: -0.0000

Data Index: 1274508 (C4 (Web Text))

Max Activating Token Index: 99

Text #2

Max Range: 1.2935. Min Range: -1.2935

Max Act: 1.2498. Min Act: -0.0001

Data Index: 1085332 (C4 (Web Text))

Max Activating Token Index: 570

Text #3

Max Range: 1.2935. Min Range: -1.2935

Max Act: 1.1061. Min Act: -0.0000

Data Index: 289897 (C4 (Web Text))

Max Activating Token Index: 190

Text #4

Max Range: 1.2935. Min Range: -1.2935

Max Act: 1.1330. Min Act: -0.0001

Data Index: 348973 (C4 (Web Text))

Max Activating Token Index: 809

Text #5

Max Range: 1.2935. Min Range: -1.2935

Max Act: 1.0974. Min Act: -0.0001

Data Index: 13391 (C4 (Web Text))

Max Activating Token Index: 261

Text #6

Max Range: 1.2935. Min Range: -1.2935

Max Act: 1.0588. Min Act: -0.0001

Data Index: 494921 (C4 (Web Text))

Max Activating Token Index: 354

Text #7

Max Range: 1.2935. Min Range: -1.2935

Max Act: 1.1433. Min Act: -0.0000

Data Index: 849727 (C4 (Web Text))

Max Activating Token Index: 577

Text #8

Max Range: 1.2935. Min Range: -1.2935

Max Act: 1.1120. Min Act: -0.0000

Data Index: 1045726 (C4 (Web Text))

Max Activating Token Index: 22

Text #9

Max Range: 1.2935. Min Range: -1.2935

Max Act: 1.1348. Min Act: -0.0001

Data Index: 1172663 (C4 (Web Text))

Max Activating Token Index: 92

Text #10

Max Range: 1.2935. Min Range: -1.2935

Max Act: 1.0695. Min Act: -0.0000

Data Index: 702261 (C4 (Web Text))

Max Activating Token Index: 2

Text #11

Max Range: 1.2935. Min Range: -1.2935

Max Act: 1.0576. Min Act: -0.0001

Data Index: 276872 (C4 (Web Text))

Max Activating Token Index: 44

Text #12

Max Range: 1.2935. Min Range: -1.2935

Max Act: 1.0202. Min Act: -0.0001

Data Index: 1026009 (C4 (Web Text))

Max Activating Token Index: 520

Text #13

Max Range: 1.2935. Min Range: -1.2935

Max Act: 1.1187. Min Act: -0.0000

Data Index: 1317604 (C4 (Web Text))

Max Activating Token Index: 236

Text #14

Max Range: 1.2935. Min Range: -1.2935

Max Act: 1.0526. Min Act: -0.0001

Data Index: 773901 (C4 (Web Text))

Max Activating Token Index: 9

Text #15

Max Range: 1.2935. Min Range: -1.2935

Max Act: 0.9949. Min Act: -0.0001

Data Index: 424130 (C4 (Web Text))

Max Activating Token Index: 72

Text #16

Max Range: 1.2935. Min Range: -1.2935

Max Act: 0.9789. Min Act: -0.0001

Data Index: 647086 (C4 (Web Text))

Max Activating Token Index: 364

Text #17

Max Range: 1.2935. Min Range: -1.2935

Max Act: 1.0375. Min Act: -0.0000

Data Index: 717090 (C4 (Web Text))

Max Activating Token Index: 695

Text #18

Max Range: 1.2935. Min Range: -1.2935

Max Act: 1.0183. Min Act: -0.0001

Data Index: 508440 (C4 (Web Text))

Max Activating Token Index: 220

Text #19

Max Range: 1.2935. Min Range: -1.2935

Max Act: 1.0997. Min Act: -0.0001

Data Index: 236112 (C4 (Web Text))

Max Activating Token Index: 249