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

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

Neuron 1034 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8280. Min Range: -2.8280

Max Act: 2.8280. Min Act: -0.0000

Data Index: 1204911 (C4 (Web Text))

Max Activating Token Index: 127

Text #1

Max Range: 2.8280. Min Range: -2.8280

Max Act: 2.8245. Min Act: -0.0000

Data Index: 493581 (C4 (Web Text))

Max Activating Token Index: 90

Text #2

Max Range: 2.8280. Min Range: -2.8280

Max Act: 2.6536. Min Act: -0.0000

Data Index: 1302641 (C4 (Web Text))

Max Activating Token Index: 264

Text #3

Max Range: 2.8280. Min Range: -2.8280

Max Act: 2.5383. Min Act: -0.0000

Data Index: 1243694 (C4 (Web Text))

Max Activating Token Index: 62

Text #4

Max Range: 2.8280. Min Range: -2.8280

Max Act: 2.4481. Min Act: -0.0000

Data Index: 265173 (C4 (Web Text))

Max Activating Token Index: 895

Text #5

Max Range: 2.8280. Min Range: -2.8280

Max Act: 2.4436. Min Act: -0.0000

Data Index: 894962 (C4 (Web Text))

Max Activating Token Index: 584

Text #6

Max Range: 2.8280. Min Range: -2.8280

Max Act: 2.2039. Min Act: 0.0000

Data Index: 1000372 (C4 (Web Text))

Max Activating Token Index: 902

Text #7

Max Range: 2.8280. Min Range: -2.8280

Max Act: 2.2843. Min Act: 0.0000

Data Index: 948280 (C4 (Web Text))

Max Activating Token Index: 40

Text #8

Max Range: 2.8280. Min Range: -2.8280

Max Act: 2.0984. Min Act: -0.0000

Data Index: 990849 (C4 (Web Text))

Max Activating Token Index: 847

Text #9

Max Range: 2.8280. Min Range: -2.8280

Max Act: 2.1054. Min Act: -0.0000

Data Index: 241731 (C4 (Web Text))

Max Activating Token Index: 981

Text #10

Max Range: 2.8280. Min Range: -2.8280

Max Act: 2.1761. Min Act: -0.0000

Data Index: 372548 (C4 (Web Text))

Max Activating Token Index: 59

Text #11

Max Range: 2.8280. Min Range: -2.8280

Max Act: 2.1766. Min Act: -0.0000

Data Index: 288078 (C4 (Web Text))

Max Activating Token Index: 39

Text #12

Max Range: 2.8280. Min Range: -2.8280

Max Act: 1.9721. Min Act: -0.0000

Data Index: 896485 (C4 (Web Text))

Max Activating Token Index: 116

Text #13

Max Range: 2.8280. Min Range: -2.8280

Max Act: 2.0112. Min Act: -0.0000

Data Index: 832929 (C4 (Web Text))

Max Activating Token Index: 932

Text #14

Max Range: 2.8280. Min Range: -2.8280

Max Act: 1.7709. Min Act: -0.0000

Data Index: 177367 (C4 (Web Text))

Max Activating Token Index: 690

Text #15

Max Range: 2.8280. Min Range: -2.8280

Max Act: 2.0013. Min Act: -0.0000

Data Index: 106410 (C4 (Web Text))

Max Activating Token Index: 601

Text #16

Max Range: 2.8280. Min Range: -2.8280

Max Act: 2.0938. Min Act: 0.0000

Data Index: 809516 (C4 (Web Text))

Max Activating Token Index: 713

Text #17

Max Range: 2.8280. Min Range: -2.8280

Max Act: 1.9661. Min Act: -0.0000

Data Index: 720426 (C4 (Web Text))

Max Activating Token Index: 462

Text #18

Max Range: 2.8280. Min Range: -2.8280

Max Act: 1.9590. Min Act: -0.0000

Data Index: 404130 (C4 (Web Text))

Max Activating Token Index: 603

Text #19

Max Range: 2.8280. Min Range: -2.8280

Max Act: 1.9583. Min Act: -0.0000

Data Index: 171913 (C4 (Web Text))

Max Activating Token Index: 698