Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2068 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.0352. Min Range: -2.0352

Max Act: 2.0053. Min Act: -0.0000

Data Index: 1437386 (Python Code)

Max Activating Token Index: 158

Text #1

Max Range: 2.0352. Min Range: -2.0352

Max Act: 2.0352. Min Act: -0.0000

Data Index: 721204 (C4 (Web Text))

Max Activating Token Index: 711

Text #2

Max Range: 2.0352. Min Range: -2.0352

Max Act: 1.9728. Min Act: -0.0000

Data Index: 1063605 (C4 (Web Text))

Max Activating Token Index: 194

Text #3

Max Range: 2.0352. Min Range: -2.0352

Max Act: 1.8216. Min Act: -0.0000

Data Index: 1132013 (C4 (Web Text))

Max Activating Token Index: 217

Text #4

Max Range: 2.0352. Min Range: -2.0352

Max Act: 1.8576. Min Act: -0.0000

Data Index: 894907 (C4 (Web Text))

Max Activating Token Index: 417

Text #5

Max Range: 2.0352. Min Range: -2.0352

Max Act: 1.4838. Min Act: -0.0000

Data Index: 1639996 (Python Code)

Max Activating Token Index: 151

Text #6

Max Range: 2.0352. Min Range: -2.0352

Max Act: 1.9155. Min Act: -0.0001

Data Index: 1440410 (Python Code)

Max Activating Token Index: 927

Text #7

Max Range: 2.0352. Min Range: -2.0352

Max Act: 2.0328. Min Act: -0.0001

Data Index: 1384516 (Python Code)

Max Activating Token Index: 794

Text #8

Max Range: 2.0352. Min Range: -2.0352

Max Act: 1.7999. Min Act: -0.0000

Data Index: 652229 (C4 (Web Text))

Max Activating Token Index: 41

Text #9

Max Range: 2.0352. Min Range: -2.0352

Max Act: 1.7002. Min Act: -0.0000

Data Index: 594835 (C4 (Web Text))

Max Activating Token Index: 231

Text #10

Max Range: 2.0352. Min Range: -2.0352

Max Act: 1.9160. Min Act: -0.0000

Data Index: 1643631 (Python Code)

Max Activating Token Index: 224

Text #11

Max Range: 2.0352. Min Range: -2.0352

Max Act: 1.7806. Min Act: -0.0000

Data Index: 1401831 (Python Code)

Max Activating Token Index: 205

Text #12

Max Range: 2.0352. Min Range: -2.0352

Max Act: 1.6603. Min Act: -0.0000

Data Index: 1651583 (Python Code)

Max Activating Token Index: 155

Text #13

Max Range: 2.0352. Min Range: -2.0352

Max Act: 1.8379. Min Act: -0.0001

Data Index: 1487526 (Python Code)

Max Activating Token Index: 667

Text #14

Max Range: 2.0352. Min Range: -2.0352

Max Act: 1.7384. Min Act: -0.0000

Data Index: 1376696 (Python Code)

Max Activating Token Index: 428

Text #15

Max Range: 2.0352. Min Range: -2.0352

Max Act: 1.6370. Min Act: -0.0000

Data Index: 1198609 (C4 (Web Text))

Max Activating Token Index: 600

Text #16

Max Range: 2.0352. Min Range: -2.0352

Max Act: 1.7183. Min Act: -0.0000

Data Index: 1398396 (Python Code)

Max Activating Token Index: 676

Text #17

Max Range: 2.0352. Min Range: -2.0352

Max Act: 1.7936. Min Act: -0.0001

Data Index: 1573548 (Python Code)

Max Activating Token Index: 729

Text #18

Max Range: 2.0352. Min Range: -2.0352

Max Act: 1.5629. Min Act: -0.0000

Data Index: 1175411 (C4 (Web Text))

Max Activating Token Index: 954

Text #19

Max Range: 2.0352. Min Range: -2.0352

Max Act: 1.5491. Min Act: -0.0000

Data Index: 88465 (C4 (Web Text))

Max Activating Token Index: 503