Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 782 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.8280. Min Range: -0.8280

Max Act: 0.8280. Min Act: -0.0000

Data Index: 1588561 (The Pile)

Max Activating Token Index: 235

Text #1

Max Range: 0.8280. Min Range: -0.8280

Max Act: 0.7800. Min Act: -0.0000

Data Index: 107346 (The Pile)

Max Activating Token Index: 239

Text #2

Max Range: 0.8280. Min Range: -0.8280

Max Act: 0.7748. Min Act: -0.0000

Data Index: 732480 (The Pile)

Max Activating Token Index: 907

Text #3

Max Range: 0.8280. Min Range: -0.8280

Max Act: 0.7257. Min Act: -0.0000

Data Index: 340377 (The Pile)

Max Activating Token Index: 210

Text #4

Max Range: 0.8280. Min Range: -0.8280

Max Act: 0.7458. Min Act: -0.0000

Data Index: 257505 (The Pile)

Max Activating Token Index: 174

Text #5

Max Range: 0.8280. Min Range: -0.8280

Max Act: 0.7388. Min Act: -0.0000

Data Index: 1226950 (The Pile)

Max Activating Token Index: 974

Text #6

Max Range: 0.8280. Min Range: -0.8280

Max Act: 0.7095. Min Act: -0.0000

Data Index: 1707164 (The Pile)

Max Activating Token Index: 97

Text #7

Max Range: 0.8280. Min Range: -0.8280

Max Act: 0.7014. Min Act: -0.0000

Data Index: 1305470 (The Pile)

Max Activating Token Index: 946

Text #8

Max Range: 0.8280. Min Range: -0.8280

Max Act: 0.6793. Min Act: -0.0000

Data Index: 195338 (The Pile)

Max Activating Token Index: 880

Text #9

Max Range: 0.8280. Min Range: -0.8280

Max Act: 0.6988. Min Act: -0.0000

Data Index: 1816928 (The Pile)

Max Activating Token Index: 113

Text #10

Max Range: 0.8280. Min Range: -0.8280

Max Act: 0.7172. Min Act: -0.0000

Data Index: 1783424 (The Pile)

Max Activating Token Index: 713

Text #11

Max Range: 0.8280. Min Range: -0.8280

Max Act: 0.6767. Min Act: -0.0000

Data Index: 888013 (The Pile)

Max Activating Token Index: 197

Text #12

Max Range: 0.8280. Min Range: -0.8280

Max Act: 0.6548. Min Act: -0.0000

Data Index: 1163734 (The Pile)

Max Activating Token Index: 929

Text #13

Max Range: 0.8280. Min Range: -0.8280

Max Act: 0.6758. Min Act: -0.0000

Data Index: 794272 (The Pile)

Max Activating Token Index: 419

Text #14

Max Range: 0.8280. Min Range: -0.8280

Max Act: 0.6964. Min Act: -0.0000

Data Index: 1915829 (The Pile)

Max Activating Token Index: 996

Text #15

Max Range: 0.8280. Min Range: -0.8280

Max Act: 0.6769. Min Act: -0.0000

Data Index: 1713922 (The Pile)

Max Activating Token Index: 568

Text #16

Max Range: 0.8280. Min Range: -0.8280

Max Act: 0.6214. Min Act: -0.0000

Data Index: 314238 (The Pile)

Max Activating Token Index: 106

Text #17

Max Range: 0.8280. Min Range: -0.8280

Max Act: 0.7062. Min Act: -0.0000

Data Index: 557664 (The Pile)

Max Activating Token Index: 513

Text #18

Max Range: 0.8280. Min Range: -0.8280

Max Act: 0.6853. Min Act: -0.0000

Data Index: 413214 (The Pile)

Max Activating Token Index: 982

Text #19

Max Range: 0.8280. Min Range: -0.8280

Max Act: 0.6941. Min Act: -0.0000

Data Index: 390263 (The Pile)

Max Activating Token Index: 538