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

Dataset: The Pile

Neuron 1127 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: 0.3003. Min Range: -0.3003

Max Act: 0.3003. Min Act: -0.0000

Data Index: 198509 (The Pile)

Max Activating Token Index: 696

Text #1

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2597. Min Act: -0.0000

Data Index: 1459127 (The Pile)

Max Activating Token Index: 939

Text #2

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2743. Min Act: -0.0000

Data Index: 1999108 (The Pile)

Max Activating Token Index: 212

Text #3

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2791. Min Act: -0.0000

Data Index: 1546696 (The Pile)

Max Activating Token Index: 9

Text #4

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2380. Min Act: -0.0000

Data Index: 1301348 (The Pile)

Max Activating Token Index: 920

Text #5

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2845. Min Act: -0.0000

Data Index: 1520723 (The Pile)

Max Activating Token Index: 570

Text #6

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2652. Min Act: -0.0000

Data Index: 683455 (The Pile)

Max Activating Token Index: 170

Text #7

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2548. Min Act: -0.0000

Data Index: 1017058 (The Pile)

Max Activating Token Index: 325

Text #8

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2295. Min Act: -0.0000

Data Index: 1016440 (The Pile)

Max Activating Token Index: 286

Text #9

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2394. Min Act: -0.0000

Data Index: 1793591 (The Pile)

Max Activating Token Index: 38

Text #10

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2307. Min Act: -0.0000

Data Index: 1323058 (The Pile)

Max Activating Token Index: 263

Text #11

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2215. Min Act: -0.0000

Data Index: 760287 (The Pile)

Max Activating Token Index: 209

Text #12

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2376. Min Act: -0.0000

Data Index: 461569 (The Pile)

Max Activating Token Index: 287

Text #13

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2237. Min Act: -0.0000

Data Index: 1518560 (The Pile)

Max Activating Token Index: 1020

Text #14

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2549. Min Act: -0.0000

Data Index: 1102019 (The Pile)

Max Activating Token Index: 106

Text #15

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2117. Min Act: -0.0000

Data Index: 218669 (The Pile)

Max Activating Token Index: 239

Text #16

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2085. Min Act: -0.0000

Data Index: 769156 (The Pile)

Max Activating Token Index: 148

Text #17

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2177. Min Act: -0.0000

Data Index: 1119764 (The Pile)

Max Activating Token Index: 156

Text #18

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.2027. Min Act: -0.0000

Data Index: 1920263 (The Pile)

Max Activating Token Index: 184

Text #19

Max Range: 0.3003. Min Range: -0.3003

Max Act: 0.1984. Min Act: -0.0000

Data Index: 1926008 (The Pile)

Max Activating Token Index: 48