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

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

Neuron 4988 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3278. Min Range: -1.3278

Max Act: 1.3278. Min Act: -0.0000

Data Index: 1623111 (Python Code)

Max Activating Token Index: 890

Text #1

Max Range: 1.3278. Min Range: -1.3278

Max Act: 1.0492. Min Act: -0.0000

Data Index: 1554300 (Python Code)

Max Activating Token Index: 795

Text #2

Max Range: 1.3278. Min Range: -1.3278

Max Act: 1.0604. Min Act: -0.0000

Data Index: 114749 (C4 (Web Text))

Max Activating Token Index: 81

Text #3

Max Range: 1.3278. Min Range: -1.3278

Max Act: 0.9906. Min Act: -0.0000

Data Index: 369232 (C4 (Web Text))

Max Activating Token Index: 91

Text #4

Max Range: 1.3278. Min Range: -1.3278

Max Act: 1.1023. Min Act: -0.0000

Data Index: 1473746 (Python Code)

Max Activating Token Index: 304

Text #5

Max Range: 1.3278. Min Range: -1.3278

Max Act: 0.9157. Min Act: -0.0000

Data Index: 1556782 (Python Code)

Max Activating Token Index: 817

Text #6

Max Range: 1.3278. Min Range: -1.3278

Max Act: 0.9325. Min Act: -0.0000

Data Index: 1139791 (C4 (Web Text))

Max Activating Token Index: 221

Text #7

Max Range: 1.3278. Min Range: -1.3278

Max Act: 0.9884. Min Act: -0.0000

Data Index: 283424 (C4 (Web Text))

Max Activating Token Index: 538

Text #8

Max Range: 1.3278. Min Range: -1.3278

Max Act: 0.9613. Min Act: -0.0000

Data Index: 232714 (C4 (Web Text))

Max Activating Token Index: 245

Text #9

Max Range: 1.3278. Min Range: -1.3278

Max Act: 1.0304. Min Act: -0.0000

Data Index: 1492517 (Python Code)

Max Activating Token Index: 97

Text #10

Max Range: 1.3278. Min Range: -1.3278

Max Act: 0.8767. Min Act: -0.0000

Data Index: 772411 (C4 (Web Text))

Max Activating Token Index: 582

Text #11

Max Range: 1.3278. Min Range: -1.3278

Max Act: 0.8526. Min Act: -0.0000

Data Index: 990998 (C4 (Web Text))

Max Activating Token Index: 392

Text #12

Max Range: 1.3278. Min Range: -1.3278

Max Act: 0.9490. Min Act: -0.0000

Data Index: 1507414 (Python Code)

Max Activating Token Index: 506

Text #13

Max Range: 1.3278. Min Range: -1.3278

Max Act: 0.9016. Min Act: -0.0000

Data Index: 230528 (C4 (Web Text))

Max Activating Token Index: 131

Text #14

Max Range: 1.3278. Min Range: -1.3278

Max Act: 0.8961. Min Act: -0.0000

Data Index: 255836 (C4 (Web Text))

Max Activating Token Index: 150

Text #15

Max Range: 1.3278. Min Range: -1.3278

Max Act: 0.8187. Min Act: -0.0000

Data Index: 1235225 (C4 (Web Text))

Max Activating Token Index: 580

Text #16

Max Range: 1.3278. Min Range: -1.3278

Max Act: 0.8289. Min Act: -0.0000

Data Index: 843829 (C4 (Web Text))

Max Activating Token Index: 391

Text #17

Max Range: 1.3278. Min Range: -1.3278

Max Act: 0.8673. Min Act: -0.0000

Data Index: 676542 (C4 (Web Text))

Max Activating Token Index: 154

Text #18

Max Range: 1.3278. Min Range: -1.3278

Max Act: 0.7808. Min Act: -0.0000

Data Index: 682929 (C4 (Web Text))

Max Activating Token Index: 656

Text #19

Max Range: 1.3278. Min Range: -1.3278

Max Act: 0.7879. Min Act: -0.0000

Data Index: 629867 (C4 (Web Text))

Max Activating Token Index: 370