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

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

Neuron 3779 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3590. Min Range: -1.3590

Max Act: 1.2926. Min Act: -0.0000

Data Index: 713059 (C4 (Web Text))

Max Activating Token Index: 125

Text #1

Max Range: 1.3590. Min Range: -1.3590

Max Act: 1.3590. Min Act: -0.0000

Data Index: 1085387 (C4 (Web Text))

Max Activating Token Index: 519

Text #2

Max Range: 1.3590. Min Range: -1.3590

Max Act: 1.2347. Min Act: -0.0000

Data Index: 170442 (C4 (Web Text))

Max Activating Token Index: 157

Text #3

Max Range: 1.3590. Min Range: -1.3590

Max Act: 1.2093. Min Act: -0.0000

Data Index: 475439 (C4 (Web Text))

Max Activating Token Index: 574

Text #4

Max Range: 1.3590. Min Range: -1.3590

Max Act: 1.0707. Min Act: -0.0000

Data Index: 614675 (C4 (Web Text))

Max Activating Token Index: 460

Text #5

Max Range: 1.3590. Min Range: -1.3590

Max Act: 1.1832. Min Act: -0.0000

Data Index: 195011 (C4 (Web Text))

Max Activating Token Index: 236

Text #6

Max Range: 1.3590. Min Range: -1.3590

Max Act: 1.0843. Min Act: -0.0000

Data Index: 748289 (C4 (Web Text))

Max Activating Token Index: 210

Text #7

Max Range: 1.3590. Min Range: -1.3590

Max Act: 1.1006. Min Act: -0.0000

Data Index: 1260093 (C4 (Web Text))

Max Activating Token Index: 1000

Text #8

Max Range: 1.3590. Min Range: -1.3590

Max Act: 1.0573. Min Act: -0.0000

Data Index: 951558 (C4 (Web Text))

Max Activating Token Index: 877

Text #9

Max Range: 1.3590. Min Range: -1.3590

Max Act: 1.0557. Min Act: -0.0000

Data Index: 151229 (C4 (Web Text))

Max Activating Token Index: 276

Text #10

Max Range: 1.3590. Min Range: -1.3590

Max Act: 0.9832. Min Act: -0.0000

Data Index: 189743 (C4 (Web Text))

Max Activating Token Index: 822

Text #11

Max Range: 1.3590. Min Range: -1.3590

Max Act: 1.0184. Min Act: -0.0000

Data Index: 1028356 (C4 (Web Text))

Max Activating Token Index: 442

Text #12

Max Range: 1.3590. Min Range: -1.3590

Max Act: 1.0510. Min Act: -0.0000

Data Index: 24538 (C4 (Web Text))

Max Activating Token Index: 857

Text #13

Max Range: 1.3590. Min Range: -1.3590

Max Act: 1.0119. Min Act: -0.0000

Data Index: 797845 (C4 (Web Text))

Max Activating Token Index: 39

Text #14

Max Range: 1.3590. Min Range: -1.3590

Max Act: 0.9744. Min Act: -0.0000

Data Index: 1172290 (C4 (Web Text))

Max Activating Token Index: 354

Text #15

Max Range: 1.3590. Min Range: -1.3590

Max Act: 0.9552. Min Act: -0.0000

Data Index: 61945 (C4 (Web Text))

Max Activating Token Index: 139

Text #16

Max Range: 1.3590. Min Range: -1.3590

Max Act: 0.9901. Min Act: -0.0000

Data Index: 1331511 (C4 (Web Text))

Max Activating Token Index: 397

Text #17

Max Range: 1.3590. Min Range: -1.3590

Max Act: 0.9182. Min Act: -0.0000

Data Index: 50811 (C4 (Web Text))

Max Activating Token Index: 277

Text #18

Max Range: 1.3590. Min Range: -1.3590

Max Act: 0.9906. Min Act: -0.0000

Data Index: 548734 (C4 (Web Text))

Max Activating Token Index: 700

Text #19

Max Range: 1.3590. Min Range: -1.3590

Max Act: 1.0141. Min Act: -0.0000

Data Index: 460734 (C4 (Web Text))

Max Activating Token Index: 373