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

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

Neuron 1319 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.7067. Min Act: -0.0000

Data Index: 1653132 (Python Code)

Max Activating Token Index: 475

Text #1

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.6645. Min Act: -0.0000

Data Index: 211683 (C4 (Web Text))

Max Activating Token Index: 622

Text #2

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.5635. Min Act: -0.0000

Data Index: 529996 (C4 (Web Text))

Max Activating Token Index: 751

Text #3

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.5367. Min Act: -0.0000

Data Index: 276251 (C4 (Web Text))

Max Activating Token Index: 38

Text #4

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.5762. Min Act: -0.0000

Data Index: 42636 (C4 (Web Text))

Max Activating Token Index: 431

Text #5

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.4805. Min Act: -0.0000

Data Index: 813896 (C4 (Web Text))

Max Activating Token Index: 994

Text #6

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.5154. Min Act: 0.0000

Data Index: 1165575 (C4 (Web Text))

Max Activating Token Index: 909

Text #7

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.5177. Min Act: -0.0000

Data Index: 1011728 (C4 (Web Text))

Max Activating Token Index: 750

Text #8

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.5277. Min Act: -0.0000

Data Index: 989367 (C4 (Web Text))

Max Activating Token Index: 981

Text #9

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.6015. Min Act: -0.0000

Data Index: 1229649 (C4 (Web Text))

Max Activating Token Index: 237

Text #10

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.4871. Min Act: -0.0000

Data Index: 713162 (C4 (Web Text))

Max Activating Token Index: 352

Text #11

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.5896. Min Act: -0.0000

Data Index: 231781 (C4 (Web Text))

Max Activating Token Index: 996

Text #12

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.5241. Min Act: -0.0000

Data Index: 284415 (C4 (Web Text))

Max Activating Token Index: 675

Text #13

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.4769. Min Act: -0.0000

Data Index: 1255818 (C4 (Web Text))

Max Activating Token Index: 986

Text #14

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.4644. Min Act: -0.0000

Data Index: 998116 (C4 (Web Text))

Max Activating Token Index: 987

Text #15

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.4618. Min Act: -0.0000

Data Index: 425137 (C4 (Web Text))

Max Activating Token Index: 615

Text #16

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.4820. Min Act: -0.0000

Data Index: 26740 (C4 (Web Text))

Max Activating Token Index: 880

Text #17

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.4688. Min Act: -0.0000

Data Index: 815209 (C4 (Web Text))

Max Activating Token Index: 217

Text #18

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.4755. Min Act: -0.0000

Data Index: 557131 (C4 (Web Text))

Max Activating Token Index: 583

Text #19

Max Range: 0.7067. Min Range: -0.7067

Max Act: 0.4779. Min Act: -0.0000

Data Index: 327126 (C4 (Web Text))

Max Activating Token Index: 238