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

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

Neuron 3020 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2928. Min Range: -1.2928

Max Act: 1.2928. Min Act: -0.0000

Data Index: 616724 (C4 (Web Text))

Max Activating Token Index: 479

Text #1

Max Range: 1.2928. Min Range: -1.2928

Max Act: 1.0132. Min Act: -0.0000

Data Index: 65339 (C4 (Web Text))

Max Activating Token Index: 446

Text #2

Max Range: 1.2928. Min Range: -1.2928

Max Act: 0.8789. Min Act: -0.0000

Data Index: 1326959 (C4 (Web Text))

Max Activating Token Index: 49

Text #3

Max Range: 1.2928. Min Range: -1.2928

Max Act: 0.8261. Min Act: -0.0000

Data Index: 735005 (C4 (Web Text))

Max Activating Token Index: 684

Text #4

Max Range: 1.2928. Min Range: -1.2928

Max Act: 0.9030. Min Act: -0.0000

Data Index: 1015789 (C4 (Web Text))

Max Activating Token Index: 430

Text #5

Max Range: 1.2928. Min Range: -1.2928

Max Act: 0.8087. Min Act: -0.0000

Data Index: 1273622 (C4 (Web Text))

Max Activating Token Index: 21

Text #6

Max Range: 1.2928. Min Range: -1.2928

Max Act: 0.7969. Min Act: -0.0000

Data Index: 35029 (C4 (Web Text))

Max Activating Token Index: 513

Text #7

Max Range: 1.2928. Min Range: -1.2928

Max Act: 0.7960. Min Act: -0.0000

Data Index: 1346328 (C4 (Web Text))

Max Activating Token Index: 449

Text #8

Max Range: 1.2928. Min Range: -1.2928

Max Act: 0.7815. Min Act: -0.0000

Data Index: 1157887 (C4 (Web Text))

Max Activating Token Index: 9

Text #9

Max Range: 1.2928. Min Range: -1.2928

Max Act: 0.7171. Min Act: -0.0000

Data Index: 73000 (C4 (Web Text))

Max Activating Token Index: 46

Text #10

Max Range: 1.2928. Min Range: -1.2928

Max Act: 0.6483. Min Act: -0.0000

Data Index: 248546 (C4 (Web Text))

Max Activating Token Index: 732

Text #11

Max Range: 1.2928. Min Range: -1.2928

Max Act: 0.6372. Min Act: -0.0000

Data Index: 1264318 (C4 (Web Text))

Max Activating Token Index: 334

Text #12

Max Range: 1.2928. Min Range: -1.2928

Max Act: 0.6504. Min Act: -0.0000

Data Index: 396601 (C4 (Web Text))

Max Activating Token Index: 635

Text #13

Max Range: 1.2928. Min Range: -1.2928

Max Act: 0.7321. Min Act: -0.0000

Data Index: 283192 (C4 (Web Text))

Max Activating Token Index: 170

Text #14

Max Range: 1.2928. Min Range: -1.2928

Max Act: 0.6881. Min Act: -0.0000

Data Index: 1233372 (C4 (Web Text))

Max Activating Token Index: 157

Text #15

Max Range: 1.2928. Min Range: -1.2928

Max Act: 0.6860. Min Act: -0.0000

Data Index: 459433 (C4 (Web Text))

Max Activating Token Index: 135

Text #16

Max Range: 1.2928. Min Range: -1.2928

Max Act: 0.7026. Min Act: -0.0000

Data Index: 703846 (C4 (Web Text))

Max Activating Token Index: 309

Text #17

Max Range: 1.2928. Min Range: -1.2928

Max Act: 0.6551. Min Act: -0.0000

Data Index: 4523 (C4 (Web Text))

Max Activating Token Index: 72

Text #18

Max Range: 1.2928. Min Range: -1.2928

Max Act: 0.6573. Min Act: -0.0000

Data Index: 985906 (C4 (Web Text))

Max Activating Token Index: 907

Text #19

Max Range: 1.2928. Min Range: -1.2928

Max Act: 0.6569. Min Act: -0.0000

Data Index: 99055 (C4 (Web Text))

Max Activating Token Index: 412