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

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

Neuron 3323 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: 4.2182. Min Range: -4.2182

Max Act: 4.1346. Min Act: -0.0000

Data Index: 699998 (C4 (Web Text))

Max Activating Token Index: 736

Text #1

Max Range: 4.2182. Min Range: -4.2182

Max Act: 4.2182. Min Act: -0.0000

Data Index: 191025 (C4 (Web Text))

Max Activating Token Index: 195

Text #2

Max Range: 4.2182. Min Range: -4.2182

Max Act: 4.2003. Min Act: 0.0001

Data Index: 258146 (C4 (Web Text))

Max Activating Token Index: 414

Text #3

Max Range: 4.2182. Min Range: -4.2182

Max Act: 3.8032. Min Act: -0.0000

Data Index: 481915 (C4 (Web Text))

Max Activating Token Index: 158

Text #4

Max Range: 4.2182. Min Range: -4.2182

Max Act: 3.6205. Min Act: 0.0001

Data Index: 159489 (C4 (Web Text))

Max Activating Token Index: 719

Text #5

Max Range: 4.2182. Min Range: -4.2182

Max Act: 3.7939. Min Act: 0.0001

Data Index: 506800 (C4 (Web Text))

Max Activating Token Index: 291

Text #6

Max Range: 4.2182. Min Range: -4.2182

Max Act: 3.5703. Min Act: 0.0001

Data Index: 407765 (C4 (Web Text))

Max Activating Token Index: 31

Text #7

Max Range: 4.2182. Min Range: -4.2182

Max Act: 3.6880. Min Act: 0.0001

Data Index: 99122 (C4 (Web Text))

Max Activating Token Index: 774

Text #8

Max Range: 4.2182. Min Range: -4.2182

Max Act: 3.7196. Min Act: 0.0000

Data Index: 1008223 (C4 (Web Text))

Max Activating Token Index: 205

Text #9

Max Range: 4.2182. Min Range: -4.2182

Max Act: 3.6872. Min Act: 0.0001

Data Index: 1099059 (C4 (Web Text))

Max Activating Token Index: 760

Text #10

Max Range: 4.2182. Min Range: -4.2182

Max Act: 3.6845. Min Act: 0.0001

Data Index: 1118597 (C4 (Web Text))

Max Activating Token Index: 845

Text #11

Max Range: 4.2182. Min Range: -4.2182

Max Act: 3.6754. Min Act: 0.0000

Data Index: 1357533 (C4 (Web Text))

Max Activating Token Index: 763

Text #12

Max Range: 4.2182. Min Range: -4.2182

Max Act: 3.6713. Min Act: 0.0001

Data Index: 902597 (C4 (Web Text))

Max Activating Token Index: 813

Text #13

Max Range: 4.2182. Min Range: -4.2182

Max Act: 3.4909. Min Act: -0.0000

Data Index: 292495 (C4 (Web Text))

Max Activating Token Index: 1017

Text #14

Max Range: 4.2182. Min Range: -4.2182

Max Act: 3.6288. Min Act: -0.0000

Data Index: 237826 (C4 (Web Text))

Max Activating Token Index: 89

Text #15

Max Range: 4.2182. Min Range: -4.2182

Max Act: 3.5442. Min Act: 0.0001

Data Index: 1101321 (C4 (Web Text))

Max Activating Token Index: 789

Text #16

Max Range: 4.2182. Min Range: -4.2182

Max Act: 3.3720. Min Act: 0.0001

Data Index: 955438 (C4 (Web Text))

Max Activating Token Index: 616

Text #17

Max Range: 4.2182. Min Range: -4.2182

Max Act: 3.3682. Min Act: 0.0001

Data Index: 734061 (C4 (Web Text))

Max Activating Token Index: 386

Text #18

Max Range: 4.2182. Min Range: -4.2182

Max Act: 3.5001. Min Act: -0.0000

Data Index: 394232 (C4 (Web Text))

Max Activating Token Index: 484

Text #19

Max Range: 4.2182. Min Range: -4.2182

Max Act: 3.4946. Min Act: -0.0000

Data Index: 989420 (C4 (Web Text))

Max Activating Token Index: 478