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

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

Neuron 4627 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2427. Min Range: -1.2427

Max Act: 1.2423. Min Act: -0.0000

Data Index: 180419 (C4 (Web Text))

Max Activating Token Index: 642

Text #1

Max Range: 1.2427. Min Range: -1.2427

Max Act: 1.2427. Min Act: -0.0000

Data Index: 1062573 (C4 (Web Text))

Max Activating Token Index: 842

Text #2

Max Range: 1.2427. Min Range: -1.2427

Max Act: 1.1662. Min Act: -0.0000

Data Index: 1046900 (C4 (Web Text))

Max Activating Token Index: 750

Text #3

Max Range: 1.2427. Min Range: -1.2427

Max Act: 1.2088. Min Act: -0.0000

Data Index: 712468 (C4 (Web Text))

Max Activating Token Index: 467

Text #4

Max Range: 1.2427. Min Range: -1.2427

Max Act: 1.1906. Min Act: -0.0000

Data Index: 1346122 (C4 (Web Text))

Max Activating Token Index: 477

Text #5

Max Range: 1.2427. Min Range: -1.2427

Max Act: 1.0821. Min Act: -0.0000

Data Index: 1284300 (C4 (Web Text))

Max Activating Token Index: 121

Text #6

Max Range: 1.2427. Min Range: -1.2427

Max Act: 1.0492. Min Act: -0.0000

Data Index: 1251671 (C4 (Web Text))

Max Activating Token Index: 476

Text #7

Max Range: 1.2427. Min Range: -1.2427

Max Act: 0.9776. Min Act: -0.0000

Data Index: 1322480 (C4 (Web Text))

Max Activating Token Index: 204

Text #8

Max Range: 1.2427. Min Range: -1.2427

Max Act: 0.9699. Min Act: -0.0000

Data Index: 376239 (C4 (Web Text))

Max Activating Token Index: 877

Text #9

Max Range: 1.2427. Min Range: -1.2427

Max Act: 0.9906. Min Act: -0.0000

Data Index: 848366 (C4 (Web Text))

Max Activating Token Index: 516

Text #10

Max Range: 1.2427. Min Range: -1.2427

Max Act: 0.9868. Min Act: -0.0000

Data Index: 461343 (C4 (Web Text))

Max Activating Token Index: 601

Text #11

Max Range: 1.2427. Min Range: -1.2427

Max Act: 0.9897. Min Act: -0.0000

Data Index: 186160 (C4 (Web Text))

Max Activating Token Index: 663

Text #12

Max Range: 1.2427. Min Range: -1.2427

Max Act: 0.9729. Min Act: -0.0000

Data Index: 754963 (C4 (Web Text))

Max Activating Token Index: 382

Text #13

Max Range: 1.2427. Min Range: -1.2427

Max Act: 1.0096. Min Act: -0.0000

Data Index: 1219331 (C4 (Web Text))

Max Activating Token Index: 740

Text #14

Max Range: 1.2427. Min Range: -1.2427

Max Act: 0.9801. Min Act: -0.0000

Data Index: 81847 (C4 (Web Text))

Max Activating Token Index: 554

Text #15

Max Range: 1.2427. Min Range: -1.2427

Max Act: 0.9647. Min Act: -0.0000

Data Index: 14331 (C4 (Web Text))

Max Activating Token Index: 912

Text #16

Max Range: 1.2427. Min Range: -1.2427

Max Act: 0.8480. Min Act: -0.0000

Data Index: 1343693 (C4 (Web Text))

Max Activating Token Index: 877

Text #17

Max Range: 1.2427. Min Range: -1.2427

Max Act: 0.8895. Min Act: -0.0000

Data Index: 209872 (C4 (Web Text))

Max Activating Token Index: 979

Text #18

Max Range: 1.2427. Min Range: -1.2427

Max Act: 0.8039. Min Act: -0.0000

Data Index: 1138620 (C4 (Web Text))

Max Activating Token Index: 802

Text #19

Max Range: 1.2427. Min Range: -1.2427

Max Act: 0.8082. Min Act: -0.0000

Data Index: 1121310 (C4 (Web Text))

Max Activating Token Index: 196