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

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

Neuron 3643 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1563. Min Range: -0.1563

Max Act: 0.1563. Min Act: -0.0001

Data Index: 261356 (C4 (Web Text))

Max Activating Token Index: 69

Text #1

Max Range: 0.1563. Min Range: -0.1563

Max Act: 0.1454. Min Act: -0.0001

Data Index: 883806 (C4 (Web Text))

Max Activating Token Index: 144

Text #2

Max Range: 0.1563. Min Range: -0.1563

Max Act: 0.1482. Min Act: -0.0001

Data Index: 289121 (C4 (Web Text))

Max Activating Token Index: 356

Text #3

Max Range: 0.1563. Min Range: -0.1563

Max Act: 0.1374. Min Act: -0.0000

Data Index: 658358 (C4 (Web Text))

Max Activating Token Index: 975

Text #4

Max Range: 0.1563. Min Range: -0.1563

Max Act: 0.1359. Min Act: -0.0001

Data Index: 1106690 (C4 (Web Text))

Max Activating Token Index: 659

Text #5

Max Range: 0.1563. Min Range: -0.1563

Max Act: 0.1095. Min Act: -0.0001

Data Index: 25685 (C4 (Web Text))

Max Activating Token Index: 977

Text #6

Max Range: 0.1563. Min Range: -0.1563

Max Act: 0.1042. Min Act: -0.0001

Data Index: 1515806 (Python Code)

Max Activating Token Index: 144

Text #7

Max Range: 0.1563. Min Range: -0.1563

Max Act: 0.0990. Min Act: -0.0000

Data Index: 283417 (C4 (Web Text))

Max Activating Token Index: 308

Text #8

Max Range: 0.1563. Min Range: -0.1563

Max Act: 0.0972. Min Act: -0.0000

Data Index: 1277292 (C4 (Web Text))

Max Activating Token Index: 1022

Text #9

Max Range: 0.1563. Min Range: -0.1563

Max Act: 0.0914. Min Act: -0.0001

Data Index: 130039 (C4 (Web Text))

Max Activating Token Index: 982

Text #10

Max Range: 0.1563. Min Range: -0.1563

Max Act: 0.0955. Min Act: -0.0001

Data Index: 963989 (C4 (Web Text))

Max Activating Token Index: 981

Text #11

Max Range: 0.1563. Min Range: -0.1563

Max Act: 0.0948. Min Act: -0.0000

Data Index: 75514 (C4 (Web Text))

Max Activating Token Index: 468

Text #12

Max Range: 0.1563. Min Range: -0.1563

Max Act: 0.0942. Min Act: -0.0001

Data Index: 1295517 (C4 (Web Text))

Max Activating Token Index: 707

Text #13

Max Range: 0.1563. Min Range: -0.1563

Max Act: 0.0955. Min Act: -0.0001

Data Index: 178614 (C4 (Web Text))

Max Activating Token Index: 970

Text #14

Max Range: 0.1563. Min Range: -0.1563

Max Act: 0.0954. Min Act: -0.0000

Data Index: 1170063 (C4 (Web Text))

Max Activating Token Index: 1001

Text #15

Max Range: 0.1563. Min Range: -0.1563

Max Act: 0.0892. Min Act: -0.0000

Data Index: 354124 (C4 (Web Text))

Max Activating Token Index: 899

Text #16

Max Range: 0.1563. Min Range: -0.1563

Max Act: 0.0878. Min Act: -0.0001

Data Index: 593913 (C4 (Web Text))

Max Activating Token Index: 1009

Text #17

Max Range: 0.1563. Min Range: -0.1563

Max Act: 0.0824. Min Act: -0.0001

Data Index: 129927 (C4 (Web Text))

Max Activating Token Index: 943

Text #18

Max Range: 0.1563. Min Range: -0.1563

Max Act: 0.0900. Min Act: -0.0000

Data Index: 209700 (C4 (Web Text))

Max Activating Token Index: 133

Text #19

Max Range: 0.1563. Min Range: -0.1563

Max Act: 0.0904. Min Act: -0.0001

Data Index: 169642 (C4 (Web Text))

Max Activating Token Index: 918