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

Dataset: The Pile

Neuron 2261 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.7897. Min Act: -0.0000

Data Index: 1587947 (The Pile)

Max Activating Token Index: 593

Text #1

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.7919. Min Act: -0.0000

Data Index: 1098942 (The Pile)

Max Activating Token Index: 363

Text #2

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.8320. Min Act: -0.0000

Data Index: 1943834 (The Pile)

Max Activating Token Index: 330

Text #3

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.8106. Min Act: -0.0000

Data Index: 1612127 (The Pile)

Max Activating Token Index: 557

Text #4

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.8148. Min Act: -0.0000

Data Index: 1201918 (The Pile)

Max Activating Token Index: 585

Text #5

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.7107. Min Act: -0.0000

Data Index: 725957 (The Pile)

Max Activating Token Index: 695

Text #6

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.6959. Min Act: -0.0000

Data Index: 1323194 (The Pile)

Max Activating Token Index: 797

Text #7

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.7563. Min Act: -0.0000

Data Index: 405964 (The Pile)

Max Activating Token Index: 80

Text #8

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.7349. Min Act: -0.0000

Data Index: 1655264 (The Pile)

Max Activating Token Index: 535

Text #9

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.7919. Min Act: -0.0000

Data Index: 278428 (The Pile)

Max Activating Token Index: 163

Text #10

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.7002. Min Act: -0.0000

Data Index: 374962 (The Pile)

Max Activating Token Index: 119

Text #11

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.7052. Min Act: -0.0000

Data Index: 361800 (The Pile)

Max Activating Token Index: 912

Text #12

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.7316. Min Act: -0.0000

Data Index: 1234082 (The Pile)

Max Activating Token Index: 220

Text #13

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.6912. Min Act: -0.0000

Data Index: 1670474 (The Pile)

Max Activating Token Index: 357

Text #14

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.7368. Min Act: -0.0000

Data Index: 171370 (The Pile)

Max Activating Token Index: 64

Text #15

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.6427. Min Act: -0.0000

Data Index: 1657645 (The Pile)

Max Activating Token Index: 85

Text #16

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.7233. Min Act: -0.0000

Data Index: 1960431 (The Pile)

Max Activating Token Index: 536

Text #17

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.7405. Min Act: -0.0000

Data Index: 459120 (The Pile)

Max Activating Token Index: 516

Text #18

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.7058. Min Act: -0.0000

Data Index: 87548 (The Pile)

Max Activating Token Index: 395

Text #19

Max Range: 0.8320. Min Range: -0.8320

Max Act: 0.6867. Min Act: -0.0000

Data Index: 612480 (The Pile)

Max Activating Token Index: 572