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

Dataset: The Pile

Neuron 2241 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: 1.6259. Min Range: -1.6259

Max Act: 1.6016. Min Act: -0.0000

Data Index: 963251 (The Pile)

Max Activating Token Index: 178

Text #1

Max Range: 1.6259. Min Range: -1.6259

Max Act: 1.5278. Min Act: -0.0000

Data Index: 1431898 (The Pile)

Max Activating Token Index: 100

Text #2

Max Range: 1.6259. Min Range: -1.6259

Max Act: 1.6259. Min Act: -0.0000

Data Index: 1927253 (The Pile)

Max Activating Token Index: 825

Text #3

Max Range: 1.6259. Min Range: -1.6259

Max Act: 1.5057. Min Act: -0.0000

Data Index: 947715 (The Pile)

Max Activating Token Index: 223

Text #4

Max Range: 1.6259. Min Range: -1.6259

Max Act: 1.5400. Min Act: -0.0000

Data Index: 1746697 (The Pile)

Max Activating Token Index: 233

Text #5

Max Range: 1.6259. Min Range: -1.6259

Max Act: 1.4379. Min Act: -0.0000

Data Index: 389579 (The Pile)

Max Activating Token Index: 282

Text #6

Max Range: 1.6259. Min Range: -1.6259

Max Act: 1.6099. Min Act: -0.0000

Data Index: 860907 (The Pile)

Max Activating Token Index: 988

Text #7

Max Range: 1.6259. Min Range: -1.6259

Max Act: 1.5181. Min Act: -0.0000

Data Index: 949258 (The Pile)

Max Activating Token Index: 350

Text #8

Max Range: 1.6259. Min Range: -1.6259

Max Act: 1.5363. Min Act: -0.0000

Data Index: 617628 (The Pile)

Max Activating Token Index: 795

Text #9

Max Range: 1.6259. Min Range: -1.6259

Max Act: 1.5154. Min Act: -0.0000

Data Index: 1344605 (The Pile)

Max Activating Token Index: 565

Text #10

Max Range: 1.6259. Min Range: -1.6259

Max Act: 1.5124. Min Act: -0.0000

Data Index: 643189 (The Pile)

Max Activating Token Index: 1010

Text #11

Max Range: 1.6259. Min Range: -1.6259

Max Act: 1.5929. Min Act: -0.0000

Data Index: 377365 (The Pile)

Max Activating Token Index: 214

Text #12

Max Range: 1.6259. Min Range: -1.6259

Max Act: 1.4450. Min Act: -0.0000

Data Index: 856580 (The Pile)

Max Activating Token Index: 387

Text #13

Max Range: 1.6259. Min Range: -1.6259

Max Act: 1.3973. Min Act: -0.0000

Data Index: 241374 (The Pile)

Max Activating Token Index: 865

Text #14

Max Range: 1.6259. Min Range: -1.6259

Max Act: 1.4728. Min Act: -0.0000

Data Index: 516651 (The Pile)

Max Activating Token Index: 1007

Text #15

Max Range: 1.6259. Min Range: -1.6259

Max Act: 1.4760. Min Act: -0.0000

Data Index: 1637260 (The Pile)

Max Activating Token Index: 406

Text #16

Max Range: 1.6259. Min Range: -1.6259

Max Act: 1.4171. Min Act: -0.0000

Data Index: 203234 (The Pile)

Max Activating Token Index: 620

Text #17

Max Range: 1.6259. Min Range: -1.6259

Max Act: 1.4197. Min Act: -0.0000

Data Index: 1710915 (The Pile)

Max Activating Token Index: 895

Text #18

Max Range: 1.6259. Min Range: -1.6259

Max Act: 1.4406. Min Act: -0.0000

Data Index: 976155 (The Pile)

Max Activating Token Index: 145

Text #19

Max Range: 1.6259. Min Range: -1.6259

Max Act: 1.3859. Min Act: -0.0000

Data Index: 157438 (The Pile)

Max Activating Token Index: 995