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

Dataset: The Pile

Neuron 4034 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.7596. Min Act: -0.0000

Data Index: 1263334 (The Pile)

Max Activating Token Index: 641

Text #1

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.7666. Min Act: -0.0000

Data Index: 856738 (The Pile)

Max Activating Token Index: 376

Text #2

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.7641. Min Act: -0.0000

Data Index: 1115327 (The Pile)

Max Activating Token Index: 605

Text #3

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.7834. Min Act: -0.0000

Data Index: 781803 (The Pile)

Max Activating Token Index: 516

Text #4

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.8248. Min Act: -0.0000

Data Index: 1673411 (The Pile)

Max Activating Token Index: 1018

Text #5

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.7342. Min Act: -0.0000

Data Index: 1095234 (The Pile)

Max Activating Token Index: 256

Text #6

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.7540. Min Act: -0.0000

Data Index: 340162 (The Pile)

Max Activating Token Index: 278

Text #7

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.7034. Min Act: -0.0000

Data Index: 100152 (The Pile)

Max Activating Token Index: 885

Text #8

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.7494. Min Act: -0.0000

Data Index: 909057 (The Pile)

Max Activating Token Index: 669

Text #9

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.6724. Min Act: -0.0000

Data Index: 1042576 (The Pile)

Max Activating Token Index: 92

Text #10

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.7026. Min Act: -0.0000

Data Index: 445263 (The Pile)

Max Activating Token Index: 257

Text #11

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.6635. Min Act: -0.0000

Data Index: 330209 (The Pile)

Max Activating Token Index: 233

Text #12

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.6556. Min Act: -0.0000

Data Index: 714259 (The Pile)

Max Activating Token Index: 790

Text #13

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.6689. Min Act: -0.0000

Data Index: 1555384 (The Pile)

Max Activating Token Index: 948

Text #14

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.6887. Min Act: -0.0000

Data Index: 951807 (The Pile)

Max Activating Token Index: 537

Text #15

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.5758. Min Act: -0.0000

Data Index: 458411 (The Pile)

Max Activating Token Index: 956

Text #16

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.6748. Min Act: -0.0000

Data Index: 1031517 (The Pile)

Max Activating Token Index: 383

Text #17

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.7013. Min Act: -0.0000

Data Index: 142178 (The Pile)

Max Activating Token Index: 810

Text #18

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.6421. Min Act: -0.0000

Data Index: 1944977 (The Pile)

Max Activating Token Index: 252

Text #19

Max Range: 0.8248. Min Range: -0.8248

Max Act: 0.5693. Min Act: -0.0000

Data Index: 1869885 (The Pile)

Max Activating Token Index: 163