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

Dataset: The Pile

Neuron 1490 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.7621. Min Act: -0.0000

Data Index: 275561 (The Pile)

Max Activating Token Index: 751

Text #1

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.6550. Min Act: -0.0000

Data Index: 1572269 (The Pile)

Max Activating Token Index: 887

Text #2

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.6334. Min Act: -0.0000

Data Index: 78686 (The Pile)

Max Activating Token Index: 475

Text #3

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.6264. Min Act: -0.0000

Data Index: 987369 (The Pile)

Max Activating Token Index: 148

Text #4

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.6600. Min Act: -0.0000

Data Index: 603236 (The Pile)

Max Activating Token Index: 400

Text #5

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.5862. Min Act: -0.0000

Data Index: 1434778 (The Pile)

Max Activating Token Index: 458

Text #6

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.6197. Min Act: -0.0000

Data Index: 1632246 (The Pile)

Max Activating Token Index: 162

Text #7

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.5286. Min Act: -0.0000

Data Index: 92720 (The Pile)

Max Activating Token Index: 742

Text #8

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.6057. Min Act: -0.0000

Data Index: 727915 (The Pile)

Max Activating Token Index: 102

Text #9

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.5073. Min Act: -0.0000

Data Index: 181109 (The Pile)

Max Activating Token Index: 792

Text #10

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.5214. Min Act: -0.0000

Data Index: 963753 (The Pile)

Max Activating Token Index: 554

Text #11

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.4871. Min Act: -0.0000

Data Index: 1090520 (The Pile)

Max Activating Token Index: 936

Text #12

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.5218. Min Act: -0.0000

Data Index: 1594797 (The Pile)

Max Activating Token Index: 473

Text #13

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.4675. Min Act: -0.0000

Data Index: 1325831 (The Pile)

Max Activating Token Index: 657

Text #14

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.4959. Min Act: -0.0000

Data Index: 323573 (The Pile)

Max Activating Token Index: 160

Text #15

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.5834. Min Act: -0.0000

Data Index: 353150 (The Pile)

Max Activating Token Index: 1014

Text #16

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.5427. Min Act: -0.0000

Data Index: 1566153 (The Pile)

Max Activating Token Index: 675

Text #17

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.4727. Min Act: -0.0000

Data Index: 1042515 (The Pile)

Max Activating Token Index: 318

Text #18

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.5174. Min Act: -0.0000

Data Index: 149350 (The Pile)

Max Activating Token Index: 628

Text #19

Max Range: 0.7621. Min Range: -0.7621

Max Act: 0.5208. Min Act: -0.0000

Data Index: 1453708 (The Pile)

Max Activating Token Index: 455