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

Dataset: The Pile

Neuron 74 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: 0.5978. Min Range: -0.5978

Max Act: 0.5978. Min Act: -0.0000

Data Index: 954401 (The Pile)

Max Activating Token Index: 597

Text #1

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.5396. Min Act: -0.0000

Data Index: 650623 (The Pile)

Max Activating Token Index: 584

Text #2

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.5790. Min Act: -0.0000

Data Index: 1951276 (The Pile)

Max Activating Token Index: 57

Text #3

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.4489. Min Act: -0.0000

Data Index: 1816547 (The Pile)

Max Activating Token Index: 946

Text #4

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.4846. Min Act: -0.0000

Data Index: 939649 (The Pile)

Max Activating Token Index: 899

Text #5

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.4640. Min Act: -0.0000

Data Index: 1151529 (The Pile)

Max Activating Token Index: 359

Text #6

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.4651. Min Act: -0.0000

Data Index: 60926 (The Pile)

Max Activating Token Index: 214

Text #7

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.4435. Min Act: -0.0000

Data Index: 1850870 (The Pile)

Max Activating Token Index: 847

Text #8

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.4432. Min Act: -0.0000

Data Index: 1574285 (The Pile)

Max Activating Token Index: 765

Text #9

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.4302. Min Act: -0.0000

Data Index: 1945679 (The Pile)

Max Activating Token Index: 31

Text #10

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.4260. Min Act: -0.0000

Data Index: 1404231 (The Pile)

Max Activating Token Index: 833

Text #11

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.4119. Min Act: -0.0000

Data Index: 833289 (The Pile)

Max Activating Token Index: 939

Text #12

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.4204. Min Act: -0.0000

Data Index: 252699 (The Pile)

Max Activating Token Index: 539

Text #13

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.4029. Min Act: -0.0000

Data Index: 546965 (The Pile)

Max Activating Token Index: 468

Text #14

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.4149. Min Act: -0.0000

Data Index: 402913 (The Pile)

Max Activating Token Index: 163

Text #15

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.4254. Min Act: -0.0000

Data Index: 234259 (The Pile)

Max Activating Token Index: 707

Text #16

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.4114. Min Act: -0.0000

Data Index: 1720081 (The Pile)

Max Activating Token Index: 426

Text #17

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.4237. Min Act: -0.0000

Data Index: 1587931 (The Pile)

Max Activating Token Index: 671

Text #18

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.4275. Min Act: -0.0000

Data Index: 122289 (The Pile)

Max Activating Token Index: 175

Text #19

Max Range: 0.5978. Min Range: -0.5978

Max Act: 0.3978. Min Act: -0.0000

Data Index: 347407 (The Pile)

Max Activating Token Index: 485