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

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

Neuron 2019 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6866. Min Range: -1.6866

Max Act: 1.6796. Min Act: -0.0000

Data Index: 1543230 (Python Code)

Max Activating Token Index: 668

Text #1

Max Range: 1.6866. Min Range: -1.6866

Max Act: 1.6866. Min Act: -0.0000

Data Index: 1561940 (Python Code)

Max Activating Token Index: 202

Text #2

Max Range: 1.6866. Min Range: -1.6866

Max Act: 1.6306. Min Act: -0.0001

Data Index: 1647125 (Python Code)

Max Activating Token Index: 265

Text #3

Max Range: 1.6866. Min Range: -1.6866

Max Act: 1.5450. Min Act: -0.0001

Data Index: 1415589 (Python Code)

Max Activating Token Index: 312

Text #4

Max Range: 1.6866. Min Range: -1.6866

Max Act: 1.5129. Min Act: -0.0000

Data Index: 1609105 (Python Code)

Max Activating Token Index: 111

Text #5

Max Range: 1.6866. Min Range: -1.6866

Max Act: 1.5044. Min Act: -0.0001

Data Index: 1368011 (Python Code)

Max Activating Token Index: 369

Text #6

Max Range: 1.6866. Min Range: -1.6866

Max Act: 1.4873. Min Act: -0.0001

Data Index: 1567690 (Python Code)

Max Activating Token Index: 108

Text #7

Max Range: 1.6866. Min Range: -1.6866

Max Act: 1.4820. Min Act: -0.0000

Data Index: 1532386 (Python Code)

Max Activating Token Index: 99

Text #8

Max Range: 1.6866. Min Range: -1.6866

Max Act: 1.4580. Min Act: -0.0001

Data Index: 1625067 (Python Code)

Max Activating Token Index: 735

Text #9

Max Range: 1.6866. Min Range: -1.6866

Max Act: 1.4121. Min Act: -0.0001

Data Index: 1578536 (Python Code)

Max Activating Token Index: 660

Text #10

Max Range: 1.6866. Min Range: -1.6866

Max Act: 1.4416. Min Act: -0.0001

Data Index: 1599358 (Python Code)

Max Activating Token Index: 633

Text #11

Max Range: 1.6866. Min Range: -1.6866

Max Act: 1.4045. Min Act: -0.0001

Data Index: 1419600 (Python Code)

Max Activating Token Index: 465

Text #12

Max Range: 1.6866. Min Range: -1.6866

Max Act: 1.4216. Min Act: -0.0000

Data Index: 1401589 (Python Code)

Max Activating Token Index: 884

Text #13

Max Range: 1.6866. Min Range: -1.6866

Max Act: 1.4013. Min Act: -0.0000

Data Index: 1613268 (Python Code)

Max Activating Token Index: 168

Text #14

Max Range: 1.6866. Min Range: -1.6866

Max Act: 1.3764. Min Act: -0.0001

Data Index: 1600055 (Python Code)

Max Activating Token Index: 982

Text #15

Max Range: 1.6866. Min Range: -1.6866

Max Act: 1.3385. Min Act: -0.0000

Data Index: 1395703 (Python Code)

Max Activating Token Index: 491

Text #16

Max Range: 1.6866. Min Range: -1.6866

Max Act: 1.3032. Min Act: -0.0001

Data Index: 1538961 (Python Code)

Max Activating Token Index: 110

Text #17

Max Range: 1.6866. Min Range: -1.6866

Max Act: 1.2789. Min Act: -0.0000

Data Index: 1573451 (Python Code)

Max Activating Token Index: 123

Text #18

Max Range: 1.6866. Min Range: -1.6866

Max Act: 1.2695. Min Act: -0.0001

Data Index: 1371168 (Python Code)

Max Activating Token Index: 751

Text #19

Max Range: 1.6866. Min Range: -1.6866

Max Act: 1.2506. Min Act: -0.0000

Data Index: 1441795 (Python Code)

Max Activating Token Index: 593