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

Dataset: The Pile

Neuron 1086 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6154. Min Range: -1.6154

Max Act: 1.6154. Min Act: -0.0000

Data Index: 1209520 (The Pile)

Max Activating Token Index: 845

Text #1

Max Range: 1.6154. Min Range: -1.6154

Max Act: 1.3274. Min Act: -0.0000

Data Index: 1139685 (The Pile)

Max Activating Token Index: 402

Text #2

Max Range: 1.6154. Min Range: -1.6154

Max Act: 1.1881. Min Act: -0.0000

Data Index: 1995076 (The Pile)

Max Activating Token Index: 670

Text #3

Max Range: 1.6154. Min Range: -1.6154

Max Act: 1.2077. Min Act: -0.0000

Data Index: 1311364 (The Pile)

Max Activating Token Index: 645

Text #4

Max Range: 1.6154. Min Range: -1.6154

Max Act: 1.0026. Min Act: -0.0000

Data Index: 1577126 (The Pile)

Max Activating Token Index: 766

Text #5

Max Range: 1.6154. Min Range: -1.6154

Max Act: 1.0477. Min Act: -0.0000

Data Index: 1579013 (The Pile)

Max Activating Token Index: 261

Text #6

Max Range: 1.6154. Min Range: -1.6154

Max Act: 1.0126. Min Act: -0.0000

Data Index: 1471819 (The Pile)

Max Activating Token Index: 633

Text #7

Max Range: 1.6154. Min Range: -1.6154

Max Act: 1.2106. Min Act: -0.0000

Data Index: 1877816 (The Pile)

Max Activating Token Index: 182

Text #8

Max Range: 1.6154. Min Range: -1.6154

Max Act: 1.2045. Min Act: -0.0000

Data Index: 134579 (The Pile)

Max Activating Token Index: 332

Text #9

Max Range: 1.6154. Min Range: -1.6154

Max Act: 1.2677. Min Act: -0.0000

Data Index: 1835029 (The Pile)

Max Activating Token Index: 561

Text #10

Max Range: 1.6154. Min Range: -1.6154

Max Act: 1.1994. Min Act: -0.0000

Data Index: 1757600 (The Pile)

Max Activating Token Index: 774

Text #11

Max Range: 1.6154. Min Range: -1.6154

Max Act: 1.1460. Min Act: -0.0000

Data Index: 211330 (The Pile)

Max Activating Token Index: 527

Text #12

Max Range: 1.6154. Min Range: -1.6154

Max Act: 1.0508. Min Act: -0.0000

Data Index: 1901927 (The Pile)

Max Activating Token Index: 642

Text #13

Max Range: 1.6154. Min Range: -1.6154

Max Act: 1.1958. Min Act: -0.0000

Data Index: 672235 (The Pile)

Max Activating Token Index: 362

Text #14

Max Range: 1.6154. Min Range: -1.6154

Max Act: 1.0903. Min Act: -0.0000

Data Index: 768221 (The Pile)

Max Activating Token Index: 382

Text #15

Max Range: 1.6154. Min Range: -1.6154

Max Act: 1.1845. Min Act: -0.0000

Data Index: 928559 (The Pile)

Max Activating Token Index: 424

Text #16

Max Range: 1.6154. Min Range: -1.6154

Max Act: 1.1033. Min Act: -0.0000

Data Index: 24806 (The Pile)

Max Activating Token Index: 360

Text #17

Max Range: 1.6154. Min Range: -1.6154

Max Act: 1.1116. Min Act: -0.0000

Data Index: 1581652 (The Pile)

Max Activating Token Index: 253

Text #18

Max Range: 1.6154. Min Range: -1.6154

Max Act: 1.0489. Min Act: -0.0000

Data Index: 700212 (The Pile)

Max Activating Token Index: 328

Text #19

Max Range: 1.6154. Min Range: -1.6154

Max Act: 1.1561. Min Act: -0.0000

Data Index: 1411356 (The Pile)

Max Activating Token Index: 565