Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 2267 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.2235. Min Act: -0.0000

Data Index: 1504670 (The Pile)

Max Activating Token Index: 392

Text #1

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.1007. Min Act: -0.0000

Data Index: 1012918 (The Pile)

Max Activating Token Index: 398

Text #2

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.0984. Min Act: -0.0000

Data Index: 281416 (The Pile)

Max Activating Token Index: 786

Text #3

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.0944. Min Act: -0.0000

Data Index: 1306421 (The Pile)

Max Activating Token Index: 488

Text #4

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.0887. Min Act: -0.0000

Data Index: 350077 (The Pile)

Max Activating Token Index: 981

Text #5

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.1010. Min Act: -0.0000

Data Index: 1066571 (The Pile)

Max Activating Token Index: 1014

Text #6

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.0879. Min Act: -0.0000

Data Index: 1568197 (The Pile)

Max Activating Token Index: 665

Text #7

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.0838. Min Act: -0.0000

Data Index: 1139224 (The Pile)

Max Activating Token Index: 595

Text #8

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.0869. Min Act: -0.0000

Data Index: 1271142 (The Pile)

Max Activating Token Index: 975

Text #9

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.0773. Min Act: -0.0000

Data Index: 533727 (The Pile)

Max Activating Token Index: 114

Text #10

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.0768. Min Act: -0.0000

Data Index: 1014316 (The Pile)

Max Activating Token Index: 165

Text #11

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.0818. Min Act: -0.0000

Data Index: 617302 (The Pile)

Max Activating Token Index: 106

Text #12

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.0796. Min Act: -0.0000

Data Index: 435494 (The Pile)

Max Activating Token Index: 616

Text #13

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.0741. Min Act: -0.0000

Data Index: 1280859 (The Pile)

Max Activating Token Index: 976

Text #14

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.0789. Min Act: -0.0000

Data Index: 1924214 (The Pile)

Max Activating Token Index: 142

Text #15

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.0807. Min Act: -0.0000

Data Index: 127476 (The Pile)

Max Activating Token Index: 1011

Text #16

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.0752. Min Act: -0.0000

Data Index: 1410582 (The Pile)

Max Activating Token Index: 1020

Text #17

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.0771. Min Act: -0.0000

Data Index: 1882169 (The Pile)

Max Activating Token Index: 236

Text #18

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.0744. Min Act: -0.0000

Data Index: 1244524 (The Pile)

Max Activating Token Index: 760

Text #19

Max Range: 0.2235. Min Range: -0.2235

Max Act: 0.0776. Min Act: -0.0000

Data Index: 291004 (The Pile)

Max Activating Token Index: 876