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

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

Neuron 3789 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3417. Min Range: -1.3417

Max Act: 1.3417. Min Act: -0.0000

Data Index: 756544 (C4 (Web Text))

Max Activating Token Index: 576

Text #1

Max Range: 1.3417. Min Range: -1.3417

Max Act: 0.9971. Min Act: -0.0000

Data Index: 267356 (C4 (Web Text))

Max Activating Token Index: 821

Text #2

Max Range: 1.3417. Min Range: -1.3417

Max Act: 0.7514. Min Act: -0.0000

Data Index: 1209802 (C4 (Web Text))

Max Activating Token Index: 262

Text #3

Max Range: 1.3417. Min Range: -1.3417

Max Act: 0.8071. Min Act: -0.0000

Data Index: 1138867 (C4 (Web Text))

Max Activating Token Index: 38

Text #4

Max Range: 1.3417. Min Range: -1.3417

Max Act: 0.8699. Min Act: -0.0000

Data Index: 1059975 (C4 (Web Text))

Max Activating Token Index: 975

Text #5

Max Range: 1.3417. Min Range: -1.3417

Max Act: 0.8381. Min Act: -0.0000

Data Index: 766905 (C4 (Web Text))

Max Activating Token Index: 618

Text #6

Max Range: 1.3417. Min Range: -1.3417

Max Act: 0.7073. Min Act: -0.0000

Data Index: 1402321 (Python Code)

Max Activating Token Index: 814

Text #7

Max Range: 1.3417. Min Range: -1.3417

Max Act: 0.6723. Min Act: -0.0000

Data Index: 1058965 (C4 (Web Text))

Max Activating Token Index: 93

Text #8

Max Range: 1.3417. Min Range: -1.3417

Max Act: 0.6487. Min Act: -0.0000

Data Index: 387543 (C4 (Web Text))

Max Activating Token Index: 647

Text #9

Max Range: 1.3417. Min Range: -1.3417

Max Act: 0.5860. Min Act: -0.0000

Data Index: 452636 (C4 (Web Text))

Max Activating Token Index: 961

Text #10

Max Range: 1.3417. Min Range: -1.3417

Max Act: 0.6119. Min Act: -0.0000

Data Index: 794711 (C4 (Web Text))

Max Activating Token Index: 895

Text #11

Max Range: 1.3417. Min Range: -1.3417

Max Act: 0.6312. Min Act: -0.0000

Data Index: 735184 (C4 (Web Text))

Max Activating Token Index: 433

Text #12

Max Range: 1.3417. Min Range: -1.3417

Max Act: 0.6071. Min Act: -0.0000

Data Index: 810831 (C4 (Web Text))

Max Activating Token Index: 807

Text #13

Max Range: 1.3417. Min Range: -1.3417

Max Act: 0.5174. Min Act: -0.0000

Data Index: 210978 (C4 (Web Text))

Max Activating Token Index: 690

Text #14

Max Range: 1.3417. Min Range: -1.3417

Max Act: 0.5241. Min Act: -0.0000

Data Index: 89697 (C4 (Web Text))

Max Activating Token Index: 363

Text #15

Max Range: 1.3417. Min Range: -1.3417

Max Act: 0.5197. Min Act: -0.0000

Data Index: 125866 (C4 (Web Text))

Max Activating Token Index: 57

Text #16

Max Range: 1.3417. Min Range: -1.3417

Max Act: 0.5025. Min Act: -0.0000

Data Index: 899264 (C4 (Web Text))

Max Activating Token Index: 151

Text #17

Max Range: 1.3417. Min Range: -1.3417

Max Act: 0.5468. Min Act: -0.0000

Data Index: 728810 (C4 (Web Text))

Max Activating Token Index: 622

Text #18

Max Range: 1.3417. Min Range: -1.3417

Max Act: 0.4915. Min Act: -0.0000

Data Index: 274590 (C4 (Web Text))

Max Activating Token Index: 661

Text #19

Max Range: 1.3417. Min Range: -1.3417

Max Act: 0.5216. Min Act: -0.0000

Data Index: 1634898 (Python Code)

Max Activating Token Index: 846