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

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

Neuron 5671 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: 1.8811. Min Range: -1.8811

Max Act: 1.8811. Min Act: -0.0000

Data Index: 1606803 (Python Code)

Max Activating Token Index: 634

Text #1

Max Range: 1.8811. Min Range: -1.8811

Max Act: 1.7283. Min Act: -0.0000

Data Index: 647690 (C4 (Web Text))

Max Activating Token Index: 806

Text #2

Max Range: 1.8811. Min Range: -1.8811

Max Act: 1.7479. Min Act: -0.0000

Data Index: 40798 (C4 (Web Text))

Max Activating Token Index: 371

Text #3

Max Range: 1.8811. Min Range: -1.8811

Max Act: 1.6504. Min Act: -0.0000

Data Index: 1636052 (Python Code)

Max Activating Token Index: 314

Text #4

Max Range: 1.8811. Min Range: -1.8811

Max Act: 1.6297. Min Act: -0.0000

Data Index: 1504643 (Python Code)

Max Activating Token Index: 921

Text #5

Max Range: 1.8811. Min Range: -1.8811

Max Act: 1.5876. Min Act: -0.0000

Data Index: 1428178 (Python Code)

Max Activating Token Index: 6

Text #6

Max Range: 1.8811. Min Range: -1.8811

Max Act: 1.5196. Min Act: -0.0000

Data Index: 1478516 (Python Code)

Max Activating Token Index: 551

Text #7

Max Range: 1.8811. Min Range: -1.8811

Max Act: 1.4787. Min Act: -0.0000

Data Index: 1210999 (C4 (Web Text))

Max Activating Token Index: 574

Text #8

Max Range: 1.8811. Min Range: -1.8811

Max Act: 1.4511. Min Act: -0.0000

Data Index: 1518161 (Python Code)

Max Activating Token Index: 716

Text #9

Max Range: 1.8811. Min Range: -1.8811

Max Act: 1.4105. Min Act: -0.0000

Data Index: 1634817 (Python Code)

Max Activating Token Index: 575

Text #10

Max Range: 1.8811. Min Range: -1.8811

Max Act: 1.4591. Min Act: -0.0000

Data Index: 1262669 (C4 (Web Text))

Max Activating Token Index: 203

Text #11

Max Range: 1.8811. Min Range: -1.8811

Max Act: 1.3503. Min Act: -0.0000

Data Index: 1436195 (Python Code)

Max Activating Token Index: 984

Text #12

Max Range: 1.8811. Min Range: -1.8811

Max Act: 1.3111. Min Act: -0.0000

Data Index: 152083 (C4 (Web Text))

Max Activating Token Index: 358

Text #13

Max Range: 1.8811. Min Range: -1.8811

Max Act: 1.3676. Min Act: -0.0000

Data Index: 84098 (C4 (Web Text))

Max Activating Token Index: 325

Text #14

Max Range: 1.8811. Min Range: -1.8811

Max Act: 1.3808. Min Act: -0.0000

Data Index: 597422 (C4 (Web Text))

Max Activating Token Index: 876

Text #15

Max Range: 1.8811. Min Range: -1.8811

Max Act: 1.3027. Min Act: -0.0000

Data Index: 223525 (C4 (Web Text))

Max Activating Token Index: 97

Text #16

Max Range: 1.8811. Min Range: -1.8811

Max Act: 1.2905. Min Act: -0.0000

Data Index: 1494429 (Python Code)

Max Activating Token Index: 275

Text #17

Max Range: 1.8811. Min Range: -1.8811

Max Act: 1.2953. Min Act: -0.0000

Data Index: 386386 (C4 (Web Text))

Max Activating Token Index: 732

Text #18

Max Range: 1.8811. Min Range: -1.8811

Max Act: 1.3671. Min Act: -0.0000

Data Index: 476036 (C4 (Web Text))

Max Activating Token Index: 418

Text #19

Max Range: 1.8811. Min Range: -1.8811

Max Act: 1.2808. Min Act: -0.0000

Data Index: 1493891 (Python Code)

Max Activating Token Index: 261