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

Dataset: The Pile

Neuron 1256 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: 0.3058. Min Range: -0.3058

Max Act: 0.3058. Min Act: -0.0000

Data Index: 121090 (The Pile)

Max Activating Token Index: 277

Text #1

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.2698. Min Act: -0.0000

Data Index: 860721 (The Pile)

Max Activating Token Index: 206

Text #2

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.2817. Min Act: -0.0000

Data Index: 1471069 (The Pile)

Max Activating Token Index: 216

Text #3

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.2607. Min Act: -0.0000

Data Index: 535544 (The Pile)

Max Activating Token Index: 910

Text #4

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.2518. Min Act: -0.0000

Data Index: 1745305 (The Pile)

Max Activating Token Index: 119

Text #5

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.2407. Min Act: -0.0000

Data Index: 1840886 (The Pile)

Max Activating Token Index: 335

Text #6

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.2258. Min Act: -0.0000

Data Index: 1079174 (The Pile)

Max Activating Token Index: 60

Text #7

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.2390. Min Act: -0.0000

Data Index: 1364513 (The Pile)

Max Activating Token Index: 263

Text #8

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.2524. Min Act: -0.0000

Data Index: 1104293 (The Pile)

Max Activating Token Index: 493

Text #9

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.2242. Min Act: -0.0000

Data Index: 1965728 (The Pile)

Max Activating Token Index: 498

Text #10

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.2170. Min Act: -0.0000

Data Index: 1900048 (The Pile)

Max Activating Token Index: 332

Text #11

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.2243. Min Act: -0.0000

Data Index: 305840 (The Pile)

Max Activating Token Index: 70

Text #12

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.1928. Min Act: -0.0000

Data Index: 611173 (The Pile)

Max Activating Token Index: 677

Text #13

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.2108. Min Act: -0.0000

Data Index: 385718 (The Pile)

Max Activating Token Index: 996

Text #14

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.2167. Min Act: -0.0000

Data Index: 1390265 (The Pile)

Max Activating Token Index: 76

Text #15

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.1948. Min Act: -0.0000

Data Index: 196323 (The Pile)

Max Activating Token Index: 857

Text #16

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.2078. Min Act: -0.0000

Data Index: 229197 (The Pile)

Max Activating Token Index: 284

Text #17

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.2143. Min Act: -0.0000

Data Index: 1512040 (The Pile)

Max Activating Token Index: 222

Text #18

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.2198. Min Act: -0.0000

Data Index: 421497 (The Pile)

Max Activating Token Index: 59

Text #19

Max Range: 0.3058. Min Range: -0.3058

Max Act: 0.2058. Min Act: -0.0000

Data Index: 1545885 (The Pile)

Max Activating Token Index: 373