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

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

Neuron 5250 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: 1.6415. Min Range: -1.6415

Max Act: 1.6415. Min Act: -0.0000

Data Index: 385640 (C4 (Web Text))

Max Activating Token Index: 907

Text #1

Max Range: 1.6415. Min Range: -1.6415

Max Act: 1.4804. Min Act: -0.0000

Data Index: 938674 (C4 (Web Text))

Max Activating Token Index: 460

Text #2

Max Range: 1.6415. Min Range: -1.6415

Max Act: 1.1563. Min Act: -0.0000

Data Index: 1217684 (C4 (Web Text))

Max Activating Token Index: 85

Text #3

Max Range: 1.6415. Min Range: -1.6415

Max Act: 1.1313. Min Act: -0.0000

Data Index: 664401 (C4 (Web Text))

Max Activating Token Index: 774

Text #4

Max Range: 1.6415. Min Range: -1.6415

Max Act: 1.0403. Min Act: -0.0000

Data Index: 1209899 (C4 (Web Text))

Max Activating Token Index: 462

Text #5

Max Range: 1.6415. Min Range: -1.6415

Max Act: 1.1398. Min Act: -0.0000

Data Index: 60556 (C4 (Web Text))

Max Activating Token Index: 952

Text #6

Max Range: 1.6415. Min Range: -1.6415

Max Act: 1.0574. Min Act: -0.0000

Data Index: 1247472 (C4 (Web Text))

Max Activating Token Index: 902

Text #7

Max Range: 1.6415. Min Range: -1.6415

Max Act: 1.0075. Min Act: -0.0000

Data Index: 1283149 (C4 (Web Text))

Max Activating Token Index: 110

Text #8

Max Range: 1.6415. Min Range: -1.6415

Max Act: 1.0071. Min Act: -0.0000

Data Index: 850217 (C4 (Web Text))

Max Activating Token Index: 194

Text #9

Max Range: 1.6415. Min Range: -1.6415

Max Act: 0.9792. Min Act: -0.0000

Data Index: 1052020 (C4 (Web Text))

Max Activating Token Index: 454

Text #10

Max Range: 1.6415. Min Range: -1.6415

Max Act: 0.9210. Min Act: -0.0000

Data Index: 57212 (C4 (Web Text))

Max Activating Token Index: 128

Text #11

Max Range: 1.6415. Min Range: -1.6415

Max Act: 0.9130. Min Act: -0.0000

Data Index: 1319654 (C4 (Web Text))

Max Activating Token Index: 665

Text #12

Max Range: 1.6415. Min Range: -1.6415

Max Act: 0.8361. Min Act: -0.0000

Data Index: 786230 (C4 (Web Text))

Max Activating Token Index: 242

Text #13

Max Range: 1.6415. Min Range: -1.6415

Max Act: 0.8872. Min Act: -0.0000

Data Index: 28583 (C4 (Web Text))

Max Activating Token Index: 970

Text #14

Max Range: 1.6415. Min Range: -1.6415

Max Act: 0.8765. Min Act: -0.0000

Data Index: 353678 (C4 (Web Text))

Max Activating Token Index: 286

Text #15

Max Range: 1.6415. Min Range: -1.6415

Max Act: 0.8712. Min Act: -0.0000

Data Index: 19092 (C4 (Web Text))

Max Activating Token Index: 584

Text #16

Max Range: 1.6415. Min Range: -1.6415

Max Act: 0.8589. Min Act: -0.0000

Data Index: 138652 (C4 (Web Text))

Max Activating Token Index: 691

Text #17

Max Range: 1.6415. Min Range: -1.6415

Max Act: 0.8619. Min Act: -0.0000

Data Index: 655864 (C4 (Web Text))

Max Activating Token Index: 184

Text #18

Max Range: 1.6415. Min Range: -1.6415

Max Act: 0.8575. Min Act: -0.0000

Data Index: 504552 (C4 (Web Text))

Max Activating Token Index: 670

Text #19

Max Range: 1.6415. Min Range: -1.6415

Max Act: 0.8575. Min Act: -0.0000

Data Index: 589323 (C4 (Web Text))

Max Activating Token Index: 894