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

Dataset: The Pile

Neuron 2694 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: 1.1022. Min Range: -1.1022

Max Act: 1.0823. Min Act: -0.0000

Data Index: 1824119 (The Pile)

Max Activating Token Index: 153

Text #1

Max Range: 1.1022. Min Range: -1.1022

Max Act: 1.0037. Min Act: -0.0000

Data Index: 824762 (The Pile)

Max Activating Token Index: 255

Text #2

Max Range: 1.1022. Min Range: -1.1022

Max Act: 1.0362. Min Act: -0.0000

Data Index: 83653 (The Pile)

Max Activating Token Index: 287

Text #3

Max Range: 1.1022. Min Range: -1.1022

Max Act: 1.0891. Min Act: -0.0000

Data Index: 1524125 (The Pile)

Max Activating Token Index: 749

Text #4

Max Range: 1.1022. Min Range: -1.1022

Max Act: 1.1022. Min Act: -0.0000

Data Index: 1768924 (The Pile)

Max Activating Token Index: 399

Text #5

Max Range: 1.1022. Min Range: -1.1022

Max Act: 1.0163. Min Act: -0.0000

Data Index: 1879466 (The Pile)

Max Activating Token Index: 299

Text #6

Max Range: 1.1022. Min Range: -1.1022

Max Act: 1.0266. Min Act: -0.0000

Data Index: 1898892 (The Pile)

Max Activating Token Index: 995

Text #7

Max Range: 1.1022. Min Range: -1.1022

Max Act: 1.0137. Min Act: -0.0000

Data Index: 1718315 (The Pile)

Max Activating Token Index: 208

Text #8

Max Range: 1.1022. Min Range: -1.1022

Max Act: 0.9926. Min Act: -0.0000

Data Index: 1749112 (The Pile)

Max Activating Token Index: 395

Text #9

Max Range: 1.1022. Min Range: -1.1022

Max Act: 0.9829. Min Act: -0.0000

Data Index: 1651590 (The Pile)

Max Activating Token Index: 759

Text #10

Max Range: 1.1022. Min Range: -1.1022

Max Act: 0.9629. Min Act: -0.0000

Data Index: 240790 (The Pile)

Max Activating Token Index: 818

Text #11

Max Range: 1.1022. Min Range: -1.1022

Max Act: 1.0385. Min Act: -0.0000

Data Index: 1610938 (The Pile)

Max Activating Token Index: 917

Text #12

Max Range: 1.1022. Min Range: -1.1022

Max Act: 0.7863. Min Act: -0.0000

Data Index: 1077120 (The Pile)

Max Activating Token Index: 1020

Text #13

Max Range: 1.1022. Min Range: -1.1022

Max Act: 0.9440. Min Act: -0.0000

Data Index: 1446763 (The Pile)

Max Activating Token Index: 243

Text #14

Max Range: 1.1022. Min Range: -1.1022

Max Act: 0.9443. Min Act: -0.0000

Data Index: 172176 (The Pile)

Max Activating Token Index: 209

Text #15

Max Range: 1.1022. Min Range: -1.1022

Max Act: 0.9035. Min Act: -0.0000

Data Index: 822151 (The Pile)

Max Activating Token Index: 92

Text #16

Max Range: 1.1022. Min Range: -1.1022

Max Act: 0.9167. Min Act: -0.0000

Data Index: 188182 (The Pile)

Max Activating Token Index: 63

Text #17

Max Range: 1.1022. Min Range: -1.1022

Max Act: 0.9409. Min Act: -0.0000

Data Index: 209769 (The Pile)

Max Activating Token Index: 165

Text #18

Max Range: 1.1022. Min Range: -1.1022

Max Act: 0.8535. Min Act: -0.0000

Data Index: 895050 (The Pile)

Max Activating Token Index: 1011

Text #19

Max Range: 1.1022. Min Range: -1.1022

Max Act: 0.9150. Min Act: -0.0000

Data Index: 1477456 (The Pile)

Max Activating Token Index: 142