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

Dataset: The Pile

Neuron 1508 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6336. Min Range: -1.6336

Max Act: 1.6336. Min Act: -0.0000

Data Index: 1158375 (The Pile)

Max Activating Token Index: 171

Text #1

Max Range: 1.6336. Min Range: -1.6336

Max Act: 1.5848. Min Act: -0.0000

Data Index: 441208 (The Pile)

Max Activating Token Index: 312

Text #2

Max Range: 1.6336. Min Range: -1.6336

Max Act: 1.4989. Min Act: -0.0000

Data Index: 1911958 (The Pile)

Max Activating Token Index: 661

Text #3

Max Range: 1.6336. Min Range: -1.6336

Max Act: 1.5037. Min Act: -0.0000

Data Index: 1285373 (The Pile)

Max Activating Token Index: 37

Text #4

Max Range: 1.6336. Min Range: -1.6336

Max Act: 1.3936. Min Act: -0.0000

Data Index: 1046300 (The Pile)

Max Activating Token Index: 754

Text #5

Max Range: 1.6336. Min Range: -1.6336

Max Act: 1.3857. Min Act: -0.0000

Data Index: 1099788 (The Pile)

Max Activating Token Index: 407

Text #6

Max Range: 1.6336. Min Range: -1.6336

Max Act: 1.3828. Min Act: -0.0000

Data Index: 1594985 (The Pile)

Max Activating Token Index: 979

Text #7

Max Range: 1.6336. Min Range: -1.6336

Max Act: 1.3673. Min Act: -0.0000

Data Index: 126485 (The Pile)

Max Activating Token Index: 951

Text #8

Max Range: 1.6336. Min Range: -1.6336

Max Act: 1.3410. Min Act: -0.0000

Data Index: 1900187 (The Pile)

Max Activating Token Index: 192

Text #9

Max Range: 1.6336. Min Range: -1.6336

Max Act: 1.3517. Min Act: -0.0000

Data Index: 1321206 (The Pile)

Max Activating Token Index: 265

Text #10

Max Range: 1.6336. Min Range: -1.6336

Max Act: 1.3067. Min Act: -0.0000

Data Index: 344451 (The Pile)

Max Activating Token Index: 700

Text #11

Max Range: 1.6336. Min Range: -1.6336

Max Act: 1.3209. Min Act: -0.0000

Data Index: 1222360 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 1.6336. Min Range: -1.6336

Max Act: 1.3024. Min Act: -0.0000

Data Index: 1187152 (The Pile)

Max Activating Token Index: 252

Text #13

Max Range: 1.6336. Min Range: -1.6336

Max Act: 1.2979. Min Act: -0.0000

Data Index: 706056 (The Pile)

Max Activating Token Index: 788

Text #14

Max Range: 1.6336. Min Range: -1.6336

Max Act: 1.3774. Min Act: -0.0000

Data Index: 1870012 (The Pile)

Max Activating Token Index: 445

Text #15

Max Range: 1.6336. Min Range: -1.6336

Max Act: 1.2979. Min Act: -0.0000

Data Index: 346178 (The Pile)

Max Activating Token Index: 463

Text #16

Max Range: 1.6336. Min Range: -1.6336

Max Act: 1.2840. Min Act: -0.0000

Data Index: 1611166 (The Pile)

Max Activating Token Index: 601

Text #17

Max Range: 1.6336. Min Range: -1.6336

Max Act: 1.2735. Min Act: -0.0000

Data Index: 475780 (The Pile)

Max Activating Token Index: 556

Text #18

Max Range: 1.6336. Min Range: -1.6336

Max Act: 1.2792. Min Act: -0.0000

Data Index: 507571 (The Pile)

Max Activating Token Index: 923

Text #19

Max Range: 1.6336. Min Range: -1.6336

Max Act: 1.2815. Min Act: -0.0000

Data Index: 1405078 (The Pile)

Max Activating Token Index: 636