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

Dataset: The Pile

Neuron 3269 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: 0.3202. Min Range: -0.3202

Max Act: 0.3202. Min Act: -0.0000

Data Index: 145360 (The Pile)

Max Activating Token Index: 20

Text #1

Max Range: 0.3202. Min Range: -0.3202

Max Act: 0.2566. Min Act: -0.0000

Data Index: 1481673 (The Pile)

Max Activating Token Index: 87

Text #2

Max Range: 0.3202. Min Range: -0.3202

Max Act: 0.2291. Min Act: -0.0000

Data Index: 1517203 (The Pile)

Max Activating Token Index: 763

Text #3

Max Range: 0.3202. Min Range: -0.3202

Max Act: 0.2245. Min Act: -0.0000

Data Index: 1565782 (The Pile)

Max Activating Token Index: 103

Text #4

Max Range: 0.3202. Min Range: -0.3202

Max Act: 0.2240. Min Act: -0.0000

Data Index: 1134771 (The Pile)

Max Activating Token Index: 788

Text #5

Max Range: 0.3202. Min Range: -0.3202

Max Act: 0.2560. Min Act: -0.0000

Data Index: 287013 (The Pile)

Max Activating Token Index: 153

Text #6

Max Range: 0.3202. Min Range: -0.3202

Max Act: 0.2167. Min Act: -0.0000

Data Index: 1926080 (The Pile)

Max Activating Token Index: 723

Text #7

Max Range: 0.3202. Min Range: -0.3202

Max Act: 0.2643. Min Act: -0.0000

Data Index: 1124714 (The Pile)

Max Activating Token Index: 177

Text #8

Max Range: 0.3202. Min Range: -0.3202

Max Act: 0.2324. Min Act: -0.0000

Data Index: 1375397 (The Pile)

Max Activating Token Index: 770

Text #9

Max Range: 0.3202. Min Range: -0.3202

Max Act: 0.2157. Min Act: -0.0000

Data Index: 1118869 (The Pile)

Max Activating Token Index: 731

Text #10

Max Range: 0.3202. Min Range: -0.3202

Max Act: 0.2357. Min Act: -0.0000

Data Index: 592798 (The Pile)

Max Activating Token Index: 551

Text #11

Max Range: 0.3202. Min Range: -0.3202

Max Act: 0.2156. Min Act: -0.0000

Data Index: 438141 (The Pile)

Max Activating Token Index: 114

Text #12

Max Range: 0.3202. Min Range: -0.3202

Max Act: 0.2233. Min Act: -0.0000

Data Index: 242820 (The Pile)

Max Activating Token Index: 685

Text #13

Max Range: 0.3202. Min Range: -0.3202

Max Act: 0.2174. Min Act: -0.0000

Data Index: 97867 (The Pile)

Max Activating Token Index: 421

Text #14

Max Range: 0.3202. Min Range: -0.3202

Max Act: 0.2127. Min Act: -0.0000

Data Index: 1617182 (The Pile)

Max Activating Token Index: 967

Text #15

Max Range: 0.3202. Min Range: -0.3202

Max Act: 0.2144. Min Act: -0.0000

Data Index: 1880918 (The Pile)

Max Activating Token Index: 128

Text #16

Max Range: 0.3202. Min Range: -0.3202

Max Act: 0.2007. Min Act: -0.0000

Data Index: 1079690 (The Pile)

Max Activating Token Index: 355

Text #17

Max Range: 0.3202. Min Range: -0.3202

Max Act: 0.2000. Min Act: -0.0000

Data Index: 1344859 (The Pile)

Max Activating Token Index: 743

Text #18

Max Range: 0.3202. Min Range: -0.3202

Max Act: 0.2334. Min Act: -0.0000

Data Index: 928478 (The Pile)

Max Activating Token Index: 667

Text #19

Max Range: 0.3202. Min Range: -0.3202

Max Act: 0.2151. Min Act: -0.0000

Data Index: 1142883 (The Pile)

Max Activating Token Index: 109