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

Dataset: The Pile

Neuron 258 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: 0.5184. Min Range: -0.5184

Max Act: 0.5184. Min Act: -0.0000

Data Index: 228946 (The Pile)

Max Activating Token Index: 94

Text #1

Max Range: 0.5184. Min Range: -0.5184

Max Act: 0.4943. Min Act: -0.0000

Data Index: 1922820 (The Pile)

Max Activating Token Index: 683

Text #2

Max Range: 0.5184. Min Range: -0.5184

Max Act: 0.5036. Min Act: -0.0000

Data Index: 587096 (The Pile)

Max Activating Token Index: 413

Text #3

Max Range: 0.5184. Min Range: -0.5184

Max Act: 0.4262. Min Act: -0.0000

Data Index: 316784 (The Pile)

Max Activating Token Index: 486

Text #4

Max Range: 0.5184. Min Range: -0.5184

Max Act: 0.4774. Min Act: -0.0000

Data Index: 445497 (The Pile)

Max Activating Token Index: 382

Text #5

Max Range: 0.5184. Min Range: -0.5184

Max Act: 0.5086. Min Act: -0.0000

Data Index: 1348396 (The Pile)

Max Activating Token Index: 672

Text #6

Max Range: 0.5184. Min Range: -0.5184

Max Act: 0.4692. Min Act: -0.0000

Data Index: 1637954 (The Pile)

Max Activating Token Index: 726

Text #7

Max Range: 0.5184. Min Range: -0.5184

Max Act: 0.4776. Min Act: -0.0000

Data Index: 1898190 (The Pile)

Max Activating Token Index: 827

Text #8

Max Range: 0.5184. Min Range: -0.5184

Max Act: 0.3686. Min Act: -0.0000

Data Index: 383779 (The Pile)

Max Activating Token Index: 1009

Text #9

Max Range: 0.5184. Min Range: -0.5184

Max Act: 0.4407. Min Act: -0.0000

Data Index: 106998 (The Pile)

Max Activating Token Index: 255

Text #10

Max Range: 0.5184. Min Range: -0.5184

Max Act: 0.4368. Min Act: -0.0000

Data Index: 885988 (The Pile)

Max Activating Token Index: 155

Text #11

Max Range: 0.5184. Min Range: -0.5184

Max Act: 0.4238. Min Act: -0.0000

Data Index: 915529 (The Pile)

Max Activating Token Index: 112

Text #12

Max Range: 0.5184. Min Range: -0.5184

Max Act: 0.4310. Min Act: -0.0000

Data Index: 1559013 (The Pile)

Max Activating Token Index: 71

Text #13

Max Range: 0.5184. Min Range: -0.5184

Max Act: 0.4251. Min Act: -0.0000

Data Index: 1480395 (The Pile)

Max Activating Token Index: 654

Text #14

Max Range: 0.5184. Min Range: -0.5184

Max Act: 0.3822. Min Act: -0.0000

Data Index: 172146 (The Pile)

Max Activating Token Index: 766

Text #15

Max Range: 0.5184. Min Range: -0.5184

Max Act: 0.3951. Min Act: -0.0000

Data Index: 1231290 (The Pile)

Max Activating Token Index: 273

Text #16

Max Range: 0.5184. Min Range: -0.5184

Max Act: 0.4187. Min Act: -0.0000

Data Index: 1400162 (The Pile)

Max Activating Token Index: 327

Text #17

Max Range: 0.5184. Min Range: -0.5184

Max Act: 0.4172. Min Act: -0.0000

Data Index: 1492302 (The Pile)

Max Activating Token Index: 61

Text #18

Max Range: 0.5184. Min Range: -0.5184

Max Act: 0.3722. Min Act: -0.0000

Data Index: 1719597 (The Pile)

Max Activating Token Index: 69

Text #19

Max Range: 0.5184. Min Range: -0.5184

Max Act: 0.4190. Min Act: -0.0000

Data Index: 1821540 (The Pile)

Max Activating Token Index: 80