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

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

Neuron 3300 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: 1.3213. Min Range: -1.3213

Max Act: 1.2491. Min Act: -0.0000

Data Index: 1042000 (C4 (Web Text))

Max Activating Token Index: 430

Text #1

Max Range: 1.3213. Min Range: -1.3213

Max Act: 1.3213. Min Act: -0.0000

Data Index: 1176124 (C4 (Web Text))

Max Activating Token Index: 627

Text #2

Max Range: 1.3213. Min Range: -1.3213

Max Act: 1.2823. Min Act: -0.0000

Data Index: 872671 (C4 (Web Text))

Max Activating Token Index: 480

Text #3

Max Range: 1.3213. Min Range: -1.3213

Max Act: 1.1882. Min Act: -0.0000

Data Index: 1199754 (C4 (Web Text))

Max Activating Token Index: 688

Text #4

Max Range: 1.3213. Min Range: -1.3213

Max Act: 0.9962. Min Act: -0.0000

Data Index: 1331671 (C4 (Web Text))

Max Activating Token Index: 164

Text #5

Max Range: 1.3213. Min Range: -1.3213

Max Act: 0.9731. Min Act: -0.0000

Data Index: 187709 (C4 (Web Text))

Max Activating Token Index: 109

Text #6

Max Range: 1.3213. Min Range: -1.3213

Max Act: 1.0417. Min Act: -0.0000

Data Index: 1114169 (C4 (Web Text))

Max Activating Token Index: 881

Text #7

Max Range: 1.3213. Min Range: -1.3213

Max Act: 0.8761. Min Act: -0.0000

Data Index: 51424 (C4 (Web Text))

Max Activating Token Index: 217

Text #8

Max Range: 1.3213. Min Range: -1.3213

Max Act: 0.8794. Min Act: -0.0000

Data Index: 166663 (C4 (Web Text))

Max Activating Token Index: 163

Text #9

Max Range: 1.3213. Min Range: -1.3213

Max Act: 0.8073. Min Act: -0.0000

Data Index: 298388 (C4 (Web Text))

Max Activating Token Index: 646

Text #10

Max Range: 1.3213. Min Range: -1.3213

Max Act: 0.8046. Min Act: -0.0000

Data Index: 229162 (C4 (Web Text))

Max Activating Token Index: 380

Text #11

Max Range: 1.3213. Min Range: -1.3213

Max Act: 0.8324. Min Act: -0.0000

Data Index: 17734 (C4 (Web Text))

Max Activating Token Index: 439

Text #12

Max Range: 1.3213. Min Range: -1.3213

Max Act: 0.7953. Min Act: -0.0000

Data Index: 750161 (C4 (Web Text))

Max Activating Token Index: 967

Text #13

Max Range: 1.3213. Min Range: -1.3213

Max Act: 0.7636. Min Act: -0.0000

Data Index: 97278 (C4 (Web Text))

Max Activating Token Index: 932

Text #14

Max Range: 1.3213. Min Range: -1.3213

Max Act: 0.7734. Min Act: -0.0000

Data Index: 107360 (C4 (Web Text))

Max Activating Token Index: 235

Text #15

Max Range: 1.3213. Min Range: -1.3213

Max Act: 0.7715. Min Act: -0.0000

Data Index: 522785 (C4 (Web Text))

Max Activating Token Index: 736

Text #16

Max Range: 1.3213. Min Range: -1.3213

Max Act: 0.7743. Min Act: -0.0000

Data Index: 1143611 (C4 (Web Text))

Max Activating Token Index: 168

Text #17

Max Range: 1.3213. Min Range: -1.3213

Max Act: 0.7534. Min Act: -0.0000

Data Index: 1203422 (C4 (Web Text))

Max Activating Token Index: 311

Text #18

Max Range: 1.3213. Min Range: -1.3213

Max Act: 0.8114. Min Act: -0.0000

Data Index: 871256 (C4 (Web Text))

Max Activating Token Index: 269

Text #19

Max Range: 1.3213. Min Range: -1.3213

Max Act: 0.7340. Min Act: -0.0000

Data Index: 1143212 (C4 (Web Text))

Max Activating Token Index: 836