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

Dataset: The Pile

Neuron 3346 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8009. Min Range: -0.8009

Max Act: 0.8009. Min Act: -0.0000

Data Index: 381017 (The Pile)

Max Activating Token Index: 633

Text #1

Max Range: 0.8009. Min Range: -0.8009

Max Act: 0.7165. Min Act: -0.0000

Data Index: 693193 (The Pile)

Max Activating Token Index: 180

Text #2

Max Range: 0.8009. Min Range: -0.8009

Max Act: 0.6947. Min Act: -0.0000

Data Index: 103720 (The Pile)

Max Activating Token Index: 868

Text #3

Max Range: 0.8009. Min Range: -0.8009

Max Act: 0.6522. Min Act: -0.0000

Data Index: 1130936 (The Pile)

Max Activating Token Index: 165

Text #4

Max Range: 0.8009. Min Range: -0.8009

Max Act: 0.5829. Min Act: -0.0000

Data Index: 1195888 (The Pile)

Max Activating Token Index: 342

Text #5

Max Range: 0.8009. Min Range: -0.8009

Max Act: 0.5419. Min Act: -0.0000

Data Index: 118988 (The Pile)

Max Activating Token Index: 409

Text #6

Max Range: 0.8009. Min Range: -0.8009

Max Act: 0.4989. Min Act: -0.0000

Data Index: 1288579 (The Pile)

Max Activating Token Index: 191

Text #7

Max Range: 0.8009. Min Range: -0.8009

Max Act: 0.5034. Min Act: -0.0000

Data Index: 118323 (The Pile)

Max Activating Token Index: 848

Text #8

Max Range: 0.8009. Min Range: -0.8009

Max Act: 0.4992. Min Act: -0.0000

Data Index: 304367 (The Pile)

Max Activating Token Index: 593

Text #9

Max Range: 0.8009. Min Range: -0.8009

Max Act: 0.5117. Min Act: -0.0000

Data Index: 1997941 (The Pile)

Max Activating Token Index: 638

Text #10

Max Range: 0.8009. Min Range: -0.8009

Max Act: 0.5441. Min Act: -0.0000

Data Index: 1379397 (The Pile)

Max Activating Token Index: 745

Text #11

Max Range: 0.8009. Min Range: -0.8009

Max Act: 0.4792. Min Act: -0.0000

Data Index: 1109563 (The Pile)

Max Activating Token Index: 477

Text #12

Max Range: 0.8009. Min Range: -0.8009

Max Act: 0.4884. Min Act: -0.0000

Data Index: 1835563 (The Pile)

Max Activating Token Index: 638

Text #13

Max Range: 0.8009. Min Range: -0.8009

Max Act: 0.4716. Min Act: -0.0000

Data Index: 98011 (The Pile)

Max Activating Token Index: 326

Text #14

Max Range: 0.8009. Min Range: -0.8009

Max Act: 0.4203. Min Act: -0.0000

Data Index: 1970733 (The Pile)

Max Activating Token Index: 630

Text #15

Max Range: 0.8009. Min Range: -0.8009

Max Act: 0.4466. Min Act: -0.0000

Data Index: 1255201 (The Pile)

Max Activating Token Index: 501

Text #16

Max Range: 0.8009. Min Range: -0.8009

Max Act: 0.4365. Min Act: -0.0000

Data Index: 1790707 (The Pile)

Max Activating Token Index: 852

Text #17

Max Range: 0.8009. Min Range: -0.8009

Max Act: 0.4176. Min Act: -0.0000

Data Index: 1540370 (The Pile)

Max Activating Token Index: 540

Text #18

Max Range: 0.8009. Min Range: -0.8009

Max Act: 0.4310. Min Act: -0.0000

Data Index: 1487616 (The Pile)

Max Activating Token Index: 603

Text #19

Max Range: 0.8009. Min Range: -0.8009

Max Act: 0.4148. Min Act: -0.0000

Data Index: 729178 (The Pile)

Max Activating Token Index: 639