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

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

Neuron 2501 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: 1.5725. Min Range: -1.5725

Max Act: 1.5725. Min Act: -0.0001

Data Index: 1200711 (C4 (Web Text))

Max Activating Token Index: 906

Text #1

Max Range: 1.5725. Min Range: -1.5725

Max Act: 1.5042. Min Act: -0.0001

Data Index: 1224276 (C4 (Web Text))

Max Activating Token Index: 816

Text #2

Max Range: 1.5725. Min Range: -1.5725

Max Act: 1.5355. Min Act: -0.0001

Data Index: 552805 (C4 (Web Text))

Max Activating Token Index: 193

Text #3

Max Range: 1.5725. Min Range: -1.5725

Max Act: 1.3857. Min Act: -0.0001

Data Index: 627943 (C4 (Web Text))

Max Activating Token Index: 228

Text #4

Max Range: 1.5725. Min Range: -1.5725

Max Act: 1.5018. Min Act: -0.0001

Data Index: 778598 (C4 (Web Text))

Max Activating Token Index: 335

Text #5

Max Range: 1.5725. Min Range: -1.5725

Max Act: 1.3619. Min Act: -0.0001

Data Index: 492595 (C4 (Web Text))

Max Activating Token Index: 36

Text #6

Max Range: 1.5725. Min Range: -1.5725

Max Act: 1.2525. Min Act: -0.0001

Data Index: 1319957 (C4 (Web Text))

Max Activating Token Index: 275

Text #7

Max Range: 1.5725. Min Range: -1.5725

Max Act: 1.3092. Min Act: -0.0001

Data Index: 321108 (C4 (Web Text))

Max Activating Token Index: 167

Text #8

Max Range: 1.5725. Min Range: -1.5725

Max Act: 1.2689. Min Act: -0.0001

Data Index: 44427 (C4 (Web Text))

Max Activating Token Index: 168

Text #9

Max Range: 1.5725. Min Range: -1.5725

Max Act: 1.1907. Min Act: -0.0001

Data Index: 490666 (C4 (Web Text))

Max Activating Token Index: 563

Text #10

Max Range: 1.5725. Min Range: -1.5725

Max Act: 1.3232. Min Act: -0.0001

Data Index: 1239691 (C4 (Web Text))

Max Activating Token Index: 321

Text #11

Max Range: 1.5725. Min Range: -1.5725

Max Act: 1.2078. Min Act: -0.0001

Data Index: 447922 (C4 (Web Text))

Max Activating Token Index: 924

Text #12

Max Range: 1.5725. Min Range: -1.5725

Max Act: 1.2729. Min Act: -0.0001

Data Index: 223351 (C4 (Web Text))

Max Activating Token Index: 918

Text #13

Max Range: 1.5725. Min Range: -1.5725

Max Act: 1.3243. Min Act: -0.0001

Data Index: 734286 (C4 (Web Text))

Max Activating Token Index: 921

Text #14

Max Range: 1.5725. Min Range: -1.5725

Max Act: 1.2913. Min Act: -0.0001

Data Index: 1088339 (C4 (Web Text))

Max Activating Token Index: 981

Text #15

Max Range: 1.5725. Min Range: -1.5725

Max Act: 1.3669. Min Act: -0.0001

Data Index: 1356264 (C4 (Web Text))

Max Activating Token Index: 331

Text #16

Max Range: 1.5725. Min Range: -1.5725

Max Act: 1.2594. Min Act: -0.0001

Data Index: 979784 (C4 (Web Text))

Max Activating Token Index: 113

Text #17

Max Range: 1.5725. Min Range: -1.5725

Max Act: 1.0643. Min Act: -0.0001

Data Index: 28037 (C4 (Web Text))

Max Activating Token Index: 162

Text #18

Max Range: 1.5725. Min Range: -1.5725

Max Act: 1.1484. Min Act: -0.0001

Data Index: 1003944 (C4 (Web Text))

Max Activating Token Index: 225

Text #19

Max Range: 1.5725. Min Range: -1.5725

Max Act: 1.1154. Min Act: -0.0001

Data Index: 565362 (C4 (Web Text))

Max Activating Token Index: 512