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

Dataset: The Pile

Neuron 3136 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2272. Min Range: -0.2272

Max Act: 0.2272. Min Act: -0.0000

Data Index: 1126089 (The Pile)

Max Activating Token Index: 43

Text #1

Max Range: 0.2272. Min Range: -0.2272

Max Act: 0.2150. Min Act: -0.0000

Data Index: 1623161 (The Pile)

Max Activating Token Index: 240

Text #2

Max Range: 0.2272. Min Range: -0.2272

Max Act: 0.2111. Min Act: -0.0000

Data Index: 1274309 (The Pile)

Max Activating Token Index: 257

Text #3

Max Range: 0.2272. Min Range: -0.2272

Max Act: 0.1939. Min Act: -0.0000

Data Index: 142121 (The Pile)

Max Activating Token Index: 387

Text #4

Max Range: 0.2272. Min Range: -0.2272

Max Act: 0.2007. Min Act: -0.0000

Data Index: 420411 (The Pile)

Max Activating Token Index: 173

Text #5

Max Range: 0.2272. Min Range: -0.2272

Max Act: 0.2003. Min Act: -0.0000

Data Index: 175081 (The Pile)

Max Activating Token Index: 212

Text #6

Max Range: 0.2272. Min Range: -0.2272

Max Act: 0.1914. Min Act: -0.0000

Data Index: 1832537 (The Pile)

Max Activating Token Index: 191

Text #7

Max Range: 0.2272. Min Range: -0.2272

Max Act: 0.1978. Min Act: -0.0000

Data Index: 1496596 (The Pile)

Max Activating Token Index: 216

Text #8

Max Range: 0.2272. Min Range: -0.2272

Max Act: 0.1956. Min Act: -0.0000

Data Index: 506016 (The Pile)

Max Activating Token Index: 189

Text #9

Max Range: 0.2272. Min Range: -0.2272

Max Act: 0.1787. Min Act: -0.0000

Data Index: 520041 (The Pile)

Max Activating Token Index: 106

Text #10

Max Range: 0.2272. Min Range: -0.2272

Max Act: 0.1896. Min Act: -0.0000

Data Index: 44657 (The Pile)

Max Activating Token Index: 580

Text #11

Max Range: 0.2272. Min Range: -0.2272

Max Act: 0.1871. Min Act: -0.0000

Data Index: 972793 (The Pile)

Max Activating Token Index: 662

Text #12

Max Range: 0.2272. Min Range: -0.2272

Max Act: 0.1865. Min Act: -0.0000

Data Index: 774731 (The Pile)

Max Activating Token Index: 241

Text #13

Max Range: 0.2272. Min Range: -0.2272

Max Act: 0.1887. Min Act: -0.0000

Data Index: 107858 (The Pile)

Max Activating Token Index: 159

Text #14

Max Range: 0.2272. Min Range: -0.2272

Max Act: 0.2002. Min Act: -0.0000

Data Index: 1233142 (The Pile)

Max Activating Token Index: 212

Text #15

Max Range: 0.2272. Min Range: -0.2272

Max Act: 0.1798. Min Act: -0.0000

Data Index: 262714 (The Pile)

Max Activating Token Index: 421

Text #16

Max Range: 0.2272. Min Range: -0.2272

Max Act: 0.1847. Min Act: -0.0000

Data Index: 1071003 (The Pile)

Max Activating Token Index: 169

Text #17

Max Range: 0.2272. Min Range: -0.2272

Max Act: 0.1825. Min Act: -0.0000

Data Index: 728020 (The Pile)

Max Activating Token Index: 692

Text #18

Max Range: 0.2272. Min Range: -0.2272

Max Act: 0.1700. Min Act: -0.0000

Data Index: 831506 (The Pile)

Max Activating Token Index: 355

Text #19

Max Range: 0.2272. Min Range: -0.2272

Max Act: 0.1652. Min Act: -0.0000

Data Index: 368190 (The Pile)

Max Activating Token Index: 37