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

Dataset: The Pile

Neuron 2568 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: 0.2394. Min Range: -0.2394

Max Act: 0.2389. Min Act: -0.0000

Data Index: 1113119 (The Pile)

Max Activating Token Index: 48

Text #1

Max Range: 0.2394. Min Range: -0.2394

Max Act: 0.2347. Min Act: -0.0000

Data Index: 1195926 (The Pile)

Max Activating Token Index: 122

Text #2

Max Range: 0.2394. Min Range: -0.2394

Max Act: 0.2089. Min Act: -0.0000

Data Index: 1621650 (The Pile)

Max Activating Token Index: 249

Text #3

Max Range: 0.2394. Min Range: -0.2394

Max Act: 0.2091. Min Act: -0.0000

Data Index: 1670488 (The Pile)

Max Activating Token Index: 861

Text #4

Max Range: 0.2394. Min Range: -0.2394

Max Act: 0.2394. Min Act: -0.0000

Data Index: 498575 (The Pile)

Max Activating Token Index: 342

Text #5

Max Range: 0.2394. Min Range: -0.2394

Max Act: 0.2120. Min Act: -0.0000

Data Index: 1538449 (The Pile)

Max Activating Token Index: 274

Text #6

Max Range: 0.2394. Min Range: -0.2394

Max Act: 0.2192. Min Act: -0.0000

Data Index: 1668417 (The Pile)

Max Activating Token Index: 300

Text #7

Max Range: 0.2394. Min Range: -0.2394

Max Act: 0.2119. Min Act: -0.0000

Data Index: 1040513 (The Pile)

Max Activating Token Index: 650

Text #8

Max Range: 0.2394. Min Range: -0.2394

Max Act: 0.2156. Min Act: -0.0000

Data Index: 1148530 (The Pile)

Max Activating Token Index: 590

Text #9

Max Range: 0.2394. Min Range: -0.2394

Max Act: 0.2137. Min Act: -0.0000

Data Index: 1940875 (The Pile)

Max Activating Token Index: 224

Text #10

Max Range: 0.2394. Min Range: -0.2394

Max Act: 0.2156. Min Act: -0.0000

Data Index: 1805979 (The Pile)

Max Activating Token Index: 121

Text #11

Max Range: 0.2394. Min Range: -0.2394

Max Act: 0.2033. Min Act: -0.0000

Data Index: 1333097 (The Pile)

Max Activating Token Index: 586

Text #12

Max Range: 0.2394. Min Range: -0.2394

Max Act: 0.2233. Min Act: -0.0000

Data Index: 879179 (The Pile)

Max Activating Token Index: 424

Text #13

Max Range: 0.2394. Min Range: -0.2394

Max Act: 0.2072. Min Act: -0.0000

Data Index: 862584 (The Pile)

Max Activating Token Index: 834

Text #14

Max Range: 0.2394. Min Range: -0.2394

Max Act: 0.1927. Min Act: -0.0000

Data Index: 1351395 (The Pile)

Max Activating Token Index: 72

Text #15

Max Range: 0.2394. Min Range: -0.2394

Max Act: 0.1867. Min Act: -0.0000

Data Index: 1859271 (The Pile)

Max Activating Token Index: 907

Text #16

Max Range: 0.2394. Min Range: -0.2394

Max Act: 0.2206. Min Act: -0.0000

Data Index: 217719 (The Pile)

Max Activating Token Index: 766

Text #17

Max Range: 0.2394. Min Range: -0.2394

Max Act: 0.2025. Min Act: -0.0000

Data Index: 1836840 (The Pile)

Max Activating Token Index: 254

Text #18

Max Range: 0.2394. Min Range: -0.2394

Max Act: 0.2193. Min Act: -0.0000

Data Index: 716796 (The Pile)

Max Activating Token Index: 464

Text #19

Max Range: 0.2394. Min Range: -0.2394

Max Act: 0.1973. Min Act: -0.0000

Data Index: 1467619 (The Pile)

Max Activating Token Index: 425