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

Dataset: The Pile

Neuron 426 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: 1.7323. Min Range: -1.7323

Max Act: 1.7323. Min Act: -0.0000

Data Index: 932275 (The Pile)

Max Activating Token Index: 438

Text #1

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.5723. Min Act: -0.0000

Data Index: 1918053 (The Pile)

Max Activating Token Index: 220

Text #2

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.6563. Min Act: -0.0000

Data Index: 1271412 (The Pile)

Max Activating Token Index: 277

Text #3

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.5135. Min Act: -0.0000

Data Index: 1377814 (The Pile)

Max Activating Token Index: 30

Text #4

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.3622. Min Act: -0.0000

Data Index: 1072729 (The Pile)

Max Activating Token Index: 71

Text #5

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.3862. Min Act: -0.0000

Data Index: 1156634 (The Pile)

Max Activating Token Index: 77

Text #6

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.3166. Min Act: -0.0000

Data Index: 1870597 (The Pile)

Max Activating Token Index: 959

Text #7

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.3899. Min Act: -0.0000

Data Index: 1746055 (The Pile)

Max Activating Token Index: 883

Text #8

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.3777. Min Act: -0.0000

Data Index: 1070442 (The Pile)

Max Activating Token Index: 703

Text #9

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.3234. Min Act: -0.0000

Data Index: 1250065 (The Pile)

Max Activating Token Index: 8

Text #10

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.3787. Min Act: -0.0000

Data Index: 1507625 (The Pile)

Max Activating Token Index: 3

Text #11

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.4043. Min Act: -0.0000

Data Index: 1223879 (The Pile)

Max Activating Token Index: 111

Text #12

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.2167. Min Act: -0.0000

Data Index: 1716427 (The Pile)

Max Activating Token Index: 17

Text #13

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.2544. Min Act: -0.0000

Data Index: 815228 (The Pile)

Max Activating Token Index: 478

Text #14

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.2831. Min Act: -0.0000

Data Index: 1321933 (The Pile)

Max Activating Token Index: 627

Text #15

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.2659. Min Act: -0.0000

Data Index: 1677532 (The Pile)

Max Activating Token Index: 263

Text #16

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.3010. Min Act: -0.0000

Data Index: 817588 (The Pile)

Max Activating Token Index: 226

Text #17

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.2621. Min Act: -0.0000

Data Index: 727245 (The Pile)

Max Activating Token Index: 427

Text #18

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.2965. Min Act: -0.0000

Data Index: 1737148 (The Pile)

Max Activating Token Index: 19

Text #19

Max Range: 1.7323. Min Range: -1.7323

Max Act: 1.2564. Min Act: -0.0000

Data Index: 1469806 (The Pile)

Max Activating Token Index: 124