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

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

Neuron 2064 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: 0.8900. Min Range: -0.8900

Max Act: 0.8093. Min Act: -0.0000

Data Index: 472476 (C4 (Web Text))

Max Activating Token Index: 749

Text #1

Max Range: 0.8900. Min Range: -0.8900

Max Act: 0.8327. Min Act: -0.0000

Data Index: 297754 (C4 (Web Text))

Max Activating Token Index: 147

Text #2

Max Range: 0.8900. Min Range: -0.8900

Max Act: 0.8691. Min Act: -0.0000

Data Index: 1247622 (C4 (Web Text))

Max Activating Token Index: 681

Text #3

Max Range: 0.8900. Min Range: -0.8900

Max Act: 0.8900. Min Act: -0.0001

Data Index: 281903 (C4 (Web Text))

Max Activating Token Index: 157

Text #4

Max Range: 0.8900. Min Range: -0.8900

Max Act: 0.8625. Min Act: -0.0000

Data Index: 1289216 (C4 (Web Text))

Max Activating Token Index: 327

Text #5

Max Range: 0.8900. Min Range: -0.8900

Max Act: 0.6356. Min Act: -0.0000

Data Index: 1183993 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 0.8900. Min Range: -0.8900

Max Act: 0.6964. Min Act: -0.0000

Data Index: 294286 (C4 (Web Text))

Max Activating Token Index: 89

Text #7

Max Range: 0.8900. Min Range: -0.8900

Max Act: 0.6874. Min Act: -0.0001

Data Index: 1076680 (C4 (Web Text))

Max Activating Token Index: 421

Text #8

Max Range: 0.8900. Min Range: -0.8900

Max Act: 0.6185. Min Act: -0.0001

Data Index: 90553 (C4 (Web Text))

Max Activating Token Index: 708

Text #9

Max Range: 0.8900. Min Range: -0.8900

Max Act: 0.6068. Min Act: -0.0000

Data Index: 356876 (C4 (Web Text))

Max Activating Token Index: 298

Text #10

Max Range: 0.8900. Min Range: -0.8900

Max Act: 0.6101. Min Act: -0.0001

Data Index: 1023363 (C4 (Web Text))

Max Activating Token Index: 971

Text #11

Max Range: 0.8900. Min Range: -0.8900

Max Act: 0.6427. Min Act: -0.0000

Data Index: 119051 (C4 (Web Text))

Max Activating Token Index: 941

Text #12

Max Range: 0.8900. Min Range: -0.8900

Max Act: 0.6831. Min Act: -0.0000

Data Index: 683164 (C4 (Web Text))

Max Activating Token Index: 660

Text #13

Max Range: 0.8900. Min Range: -0.8900

Max Act: 0.6524. Min Act: -0.0000

Data Index: 125573 (C4 (Web Text))

Max Activating Token Index: 24

Text #14

Max Range: 0.8900. Min Range: -0.8900

Max Act: 0.5615. Min Act: -0.0001

Data Index: 943570 (C4 (Web Text))

Max Activating Token Index: 451

Text #15

Max Range: 0.8900. Min Range: -0.8900

Max Act: 0.6196. Min Act: -0.0001

Data Index: 674541 (C4 (Web Text))

Max Activating Token Index: 283

Text #16

Max Range: 0.8900. Min Range: -0.8900

Max Act: 0.5427. Min Act: -0.0000

Data Index: 104557 (C4 (Web Text))

Max Activating Token Index: 293

Text #17

Max Range: 0.8900. Min Range: -0.8900

Max Act: 0.5186. Min Act: -0.0001

Data Index: 117594 (C4 (Web Text))

Max Activating Token Index: 996

Text #18

Max Range: 0.8900. Min Range: -0.8900

Max Act: 0.5268. Min Act: -0.0001

Data Index: 47591 (C4 (Web Text))

Max Activating Token Index: 54

Text #19

Max Range: 0.8900. Min Range: -0.8900

Max Act: 0.5379. Min Act: -0.0001

Data Index: 1119669 (C4 (Web Text))

Max Activating Token Index: 553