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

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

Neuron 5071 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3085. Min Range: -2.3085

Max Act: 2.3085. Min Act: -0.0000

Data Index: 588561 (C4 (Web Text))

Max Activating Token Index: 972

Text #1

Max Range: 2.3085. Min Range: -2.3085

Max Act: 2.1000. Min Act: -0.0000

Data Index: 1294217 (C4 (Web Text))

Max Activating Token Index: 944

Text #2

Max Range: 2.3085. Min Range: -2.3085

Max Act: 1.9256. Min Act: -0.0000

Data Index: 1150989 (C4 (Web Text))

Max Activating Token Index: 638

Text #3

Max Range: 2.3085. Min Range: -2.3085

Max Act: 1.9178. Min Act: -0.0000

Data Index: 314631 (C4 (Web Text))

Max Activating Token Index: 859

Text #4

Max Range: 2.3085. Min Range: -2.3085

Max Act: 1.7733. Min Act: -0.0000

Data Index: 434827 (C4 (Web Text))

Max Activating Token Index: 885

Text #5

Max Range: 2.3085. Min Range: -2.3085

Max Act: 1.7048. Min Act: -0.0000

Data Index: 1101649 (C4 (Web Text))

Max Activating Token Index: 888

Text #6

Max Range: 2.3085. Min Range: -2.3085

Max Act: 1.6121. Min Act: -0.0000

Data Index: 423268 (C4 (Web Text))

Max Activating Token Index: 620

Text #7

Max Range: 2.3085. Min Range: -2.3085

Max Act: 1.6185. Min Act: -0.0000

Data Index: 709022 (C4 (Web Text))

Max Activating Token Index: 157

Text #8

Max Range: 2.3085. Min Range: -2.3085

Max Act: 1.5462. Min Act: -0.0000

Data Index: 1356080 (C4 (Web Text))

Max Activating Token Index: 29

Text #9

Max Range: 2.3085. Min Range: -2.3085

Max Act: 1.5417. Min Act: -0.0000

Data Index: 964840 (C4 (Web Text))

Max Activating Token Index: 557

Text #10

Max Range: 2.3085. Min Range: -2.3085

Max Act: 1.5077. Min Act: -0.0000

Data Index: 177343 (C4 (Web Text))

Max Activating Token Index: 745

Text #11

Max Range: 2.3085. Min Range: -2.3085

Max Act: 1.4237. Min Act: -0.0000

Data Index: 1046755 (C4 (Web Text))

Max Activating Token Index: 954

Text #12

Max Range: 2.3085. Min Range: -2.3085

Max Act: 1.5144. Min Act: -0.0000

Data Index: 744160 (C4 (Web Text))

Max Activating Token Index: 923

Text #13

Max Range: 2.3085. Min Range: -2.3085

Max Act: 1.5363. Min Act: -0.0000

Data Index: 43733 (C4 (Web Text))

Max Activating Token Index: 971

Text #14

Max Range: 2.3085. Min Range: -2.3085

Max Act: 1.4527. Min Act: -0.0000

Data Index: 576699 (C4 (Web Text))

Max Activating Token Index: 233

Text #15

Max Range: 2.3085. Min Range: -2.3085

Max Act: 1.4531. Min Act: -0.0000

Data Index: 693435 (C4 (Web Text))

Max Activating Token Index: 67

Text #16

Max Range: 2.3085. Min Range: -2.3085

Max Act: 1.2996. Min Act: -0.0000

Data Index: 1072122 (C4 (Web Text))

Max Activating Token Index: 932

Text #17

Max Range: 2.3085. Min Range: -2.3085

Max Act: 1.3580. Min Act: -0.0000

Data Index: 1143130 (C4 (Web Text))

Max Activating Token Index: 948

Text #18

Max Range: 2.3085. Min Range: -2.3085

Max Act: 1.4260. Min Act: -0.0000

Data Index: 761294 (C4 (Web Text))

Max Activating Token Index: 971

Text #19

Max Range: 2.3085. Min Range: -2.3085

Max Act: 1.3765. Min Act: -0.0000

Data Index: 360338 (C4 (Web Text))

Max Activating Token Index: 502