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

Dataset: The Pile

Neuron 1436 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.9184. Min Act: -0.0000

Data Index: 894899 (The Pile)

Max Activating Token Index: 257

Text #1

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.8012. Min Act: -0.0000

Data Index: 1702728 (The Pile)

Max Activating Token Index: 109

Text #2

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.7868. Min Act: -0.0000

Data Index: 475606 (The Pile)

Max Activating Token Index: 849

Text #3

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.6885. Min Act: -0.0000

Data Index: 1653658 (The Pile)

Max Activating Token Index: 763

Text #4

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.7977. Min Act: -0.0000

Data Index: 637750 (The Pile)

Max Activating Token Index: 226

Text #5

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.7321. Min Act: -0.0000

Data Index: 1686820 (The Pile)

Max Activating Token Index: 956

Text #6

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.7632. Min Act: -0.0000

Data Index: 507967 (The Pile)

Max Activating Token Index: 366

Text #7

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.7000. Min Act: -0.0000

Data Index: 384815 (The Pile)

Max Activating Token Index: 953

Text #8

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.7360. Min Act: -0.0000

Data Index: 1515890 (The Pile)

Max Activating Token Index: 170

Text #9

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.7092. Min Act: -0.0000

Data Index: 868824 (The Pile)

Max Activating Token Index: 735

Text #10

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.6836. Min Act: -0.0000

Data Index: 599247 (The Pile)

Max Activating Token Index: 344

Text #11

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.6525. Min Act: -0.0000

Data Index: 1464961 (The Pile)

Max Activating Token Index: 283

Text #12

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.6894. Min Act: -0.0000

Data Index: 434356 (The Pile)

Max Activating Token Index: 298

Text #13

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.6419. Min Act: -0.0000

Data Index: 431587 (The Pile)

Max Activating Token Index: 538

Text #14

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.6632. Min Act: -0.0000

Data Index: 1753284 (The Pile)

Max Activating Token Index: 102

Text #15

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.6715. Min Act: -0.0000

Data Index: 862988 (The Pile)

Max Activating Token Index: 341

Text #16

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.6255. Min Act: -0.0000

Data Index: 246653 (The Pile)

Max Activating Token Index: 256

Text #17

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.6257. Min Act: -0.0000

Data Index: 1027488 (The Pile)

Max Activating Token Index: 219

Text #18

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.6239. Min Act: -0.0000

Data Index: 1676272 (The Pile)

Max Activating Token Index: 333

Text #19

Max Range: 0.9184. Min Range: -0.9184

Max Act: 0.6091. Min Act: -0.0000

Data Index: 408945 (The Pile)

Max Activating Token Index: 117