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

Dataset: The Pile

Neuron 662 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8179. Min Range: -0.8179

Max Act: 0.7982. Min Act: 0.0000

Data Index: 1311132 (The Pile)

Max Activating Token Index: 83

Text #1

Max Range: 0.8179. Min Range: -0.8179

Max Act: 0.8179. Min Act: -0.0000

Data Index: 1985260 (The Pile)

Max Activating Token Index: 142

Text #2

Max Range: 0.8179. Min Range: -0.8179

Max Act: 0.7140. Min Act: -0.0000

Data Index: 1435630 (The Pile)

Max Activating Token Index: 858

Text #3

Max Range: 0.8179. Min Range: -0.8179

Max Act: 0.7058. Min Act: 0.0000

Data Index: 1231282 (The Pile)

Max Activating Token Index: 329

Text #4

Max Range: 0.8179. Min Range: -0.8179

Max Act: 0.7119. Min Act: -0.0000

Data Index: 1930098 (The Pile)

Max Activating Token Index: 460

Text #5

Max Range: 0.8179. Min Range: -0.8179

Max Act: 0.6618. Min Act: -0.0000

Data Index: 169784 (The Pile)

Max Activating Token Index: 192

Text #6

Max Range: 0.8179. Min Range: -0.8179

Max Act: 0.6293. Min Act: -0.0000

Data Index: 237753 (The Pile)

Max Activating Token Index: 430

Text #7

Max Range: 0.8179. Min Range: -0.8179

Max Act: 0.6165. Min Act: -0.0000

Data Index: 621996 (The Pile)

Max Activating Token Index: 128

Text #8

Max Range: 0.8179. Min Range: -0.8179

Max Act: 0.6021. Min Act: -0.0000

Data Index: 221499 (The Pile)

Max Activating Token Index: 173

Text #9

Max Range: 0.8179. Min Range: -0.8179

Max Act: 0.6063. Min Act: -0.0000

Data Index: 1597578 (The Pile)

Max Activating Token Index: 70

Text #10

Max Range: 0.8179. Min Range: -0.8179

Max Act: 0.6161. Min Act: -0.0000

Data Index: 1738673 (The Pile)

Max Activating Token Index: 191

Text #11

Max Range: 0.8179. Min Range: -0.8179

Max Act: 0.5605. Min Act: -0.0000

Data Index: 734253 (The Pile)

Max Activating Token Index: 760

Text #12

Max Range: 0.8179. Min Range: -0.8179

Max Act: 0.6037. Min Act: -0.0000

Data Index: 354260 (The Pile)

Max Activating Token Index: 137

Text #13

Max Range: 0.8179. Min Range: -0.8179

Max Act: 0.5710. Min Act: -0.0000

Data Index: 1939346 (The Pile)

Max Activating Token Index: 578

Text #14

Max Range: 0.8179. Min Range: -0.8179

Max Act: 0.6317. Min Act: -0.0000

Data Index: 310833 (The Pile)

Max Activating Token Index: 315

Text #15

Max Range: 0.8179. Min Range: -0.8179

Max Act: 0.5918. Min Act: -0.0000

Data Index: 935076 (The Pile)

Max Activating Token Index: 890

Text #16

Max Range: 0.8179. Min Range: -0.8179

Max Act: 0.6030. Min Act: -0.0000

Data Index: 1131746 (The Pile)

Max Activating Token Index: 327

Text #17

Max Range: 0.8179. Min Range: -0.8179

Max Act: 0.6045. Min Act: -0.0000

Data Index: 466462 (The Pile)

Max Activating Token Index: 340

Text #18

Max Range: 0.8179. Min Range: -0.8179

Max Act: 0.5558. Min Act: -0.0000

Data Index: 48127 (The Pile)

Max Activating Token Index: 446

Text #19

Max Range: 0.8179. Min Range: -0.8179

Max Act: 0.6091. Min Act: -0.0000

Data Index: 432481 (The Pile)

Max Activating Token Index: 427