Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 4091 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.6233. Min Act: -0.0000

Data Index: 1706353 (The Pile)

Max Activating Token Index: 176

Text #1

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.5180. Min Act: -0.0000

Data Index: 896972 (The Pile)

Max Activating Token Index: 730

Text #2

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.5367. Min Act: -0.0000

Data Index: 1196918 (The Pile)

Max Activating Token Index: 300

Text #3

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.4872. Min Act: -0.0000

Data Index: 1983228 (The Pile)

Max Activating Token Index: 230

Text #4

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.4363. Min Act: -0.0000

Data Index: 1000922 (The Pile)

Max Activating Token Index: 147

Text #5

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.4403. Min Act: -0.0000

Data Index: 1523191 (The Pile)

Max Activating Token Index: 782

Text #6

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.4441. Min Act: -0.0000

Data Index: 1440899 (The Pile)

Max Activating Token Index: 402

Text #7

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.4398. Min Act: -0.0000

Data Index: 907911 (The Pile)

Max Activating Token Index: 735

Text #8

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.4088. Min Act: -0.0000

Data Index: 250213 (The Pile)

Max Activating Token Index: 801

Text #9

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.4195. Min Act: -0.0000

Data Index: 610678 (The Pile)

Max Activating Token Index: 408

Text #10

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.4272. Min Act: -0.0000

Data Index: 746757 (The Pile)

Max Activating Token Index: 437

Text #11

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.3879. Min Act: -0.0000

Data Index: 1926615 (The Pile)

Max Activating Token Index: 499

Text #12

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.3724. Min Act: -0.0000

Data Index: 1943803 (The Pile)

Max Activating Token Index: 500

Text #13

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.4095. Min Act: -0.0000

Data Index: 1581363 (The Pile)

Max Activating Token Index: 837

Text #14

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.3988. Min Act: -0.0000

Data Index: 1330522 (The Pile)

Max Activating Token Index: 961

Text #15

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.4064. Min Act: -0.0000

Data Index: 296647 (The Pile)

Max Activating Token Index: 214

Text #16

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.4453. Min Act: -0.0000

Data Index: 899460 (The Pile)

Max Activating Token Index: 420

Text #17

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.3804. Min Act: -0.0000

Data Index: 966523 (The Pile)

Max Activating Token Index: 260

Text #18

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.3921. Min Act: -0.0000

Data Index: 552000 (The Pile)

Max Activating Token Index: 621

Text #19

Max Range: 0.6233. Min Range: -0.6233

Max Act: 0.4028. Min Act: -0.0000

Data Index: 1719944 (The Pile)

Max Activating Token Index: 776