Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 636 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0508. Min Act: -0.0003

Data Index: 789423 (C4 (Web Text))

Max Activating Token Index: 303

Text #1

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0396. Min Act: -0.0003

Data Index: 807266 (C4 (Web Text))

Max Activating Token Index: 298

Text #2

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0402. Min Act: -0.0003

Data Index: 246932 (C4 (Web Text))

Max Activating Token Index: 247

Text #3

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0374. Min Act: -0.0003

Data Index: 436900 (C4 (Web Text))

Max Activating Token Index: 734

Text #4

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0368. Min Act: -0.0003

Data Index: 834973 (C4 (Web Text))

Max Activating Token Index: 636

Text #5

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0382. Min Act: -0.0003

Data Index: 1126920 (C4 (Web Text))

Max Activating Token Index: 953

Text #6

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0354. Min Act: -0.0004

Data Index: 155404 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0364. Min Act: -0.0003

Data Index: 724022 (C4 (Web Text))

Max Activating Token Index: 110

Text #8

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0344. Min Act: -0.0003

Data Index: 784237 (C4 (Web Text))

Max Activating Token Index: 65

Text #9

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0368. Min Act: -0.0004

Data Index: 1248749 (C4 (Web Text))

Max Activating Token Index: 386

Text #10

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0354. Min Act: -0.0003

Data Index: 681367 (C4 (Web Text))

Max Activating Token Index: 582

Text #11

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0343. Min Act: -0.0003

Data Index: 1333689 (C4 (Web Text))

Max Activating Token Index: 565

Text #12

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0340. Min Act: -0.0004

Data Index: 127896 (C4 (Web Text))

Max Activating Token Index: 1011

Text #13

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0359. Min Act: -0.0003

Data Index: 1019031 (C4 (Web Text))

Max Activating Token Index: 904

Text #14

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0343. Min Act: -0.0003

Data Index: 252912 (C4 (Web Text))

Max Activating Token Index: 61

Text #15

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0354. Min Act: -0.0003

Data Index: 859084 (C4 (Web Text))

Max Activating Token Index: 271

Text #16

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0327. Min Act: -0.0003

Data Index: 1017295 (C4 (Web Text))

Max Activating Token Index: 601

Text #17

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0324. Min Act: -0.0003

Data Index: 816778 (C4 (Web Text))

Max Activating Token Index: 822

Text #18

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0343. Min Act: -0.0003

Data Index: 110658 (C4 (Web Text))

Max Activating Token Index: 54

Text #19

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0302. Min Act: -0.0003

Data Index: 18463 (C4 (Web Text))

Max Activating Token Index: 331