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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3211 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5264. Min Range: -1.5264

Max Act: 1.5264. Min Act: -0.0002

Data Index: 156020 (C4 (Web Text))

Max Activating Token Index: 984

Text #1

Max Range: 1.5264. Min Range: -1.5264

Max Act: 1.5022. Min Act: -0.0002

Data Index: 872587 (C4 (Web Text))

Max Activating Token Index: 302

Text #2

Max Range: 1.5264. Min Range: -1.5264

Max Act: 1.4364. Min Act: -0.0002

Data Index: 1140206 (C4 (Web Text))

Max Activating Token Index: 292

Text #3

Max Range: 1.5264. Min Range: -1.5264

Max Act: 1.3151. Min Act: -0.0002

Data Index: 1253122 (C4 (Web Text))

Max Activating Token Index: 252

Text #4

Max Range: 1.5264. Min Range: -1.5264

Max Act: 1.3536. Min Act: -0.0002

Data Index: 342164 (C4 (Web Text))

Max Activating Token Index: 111

Text #5

Max Range: 1.5264. Min Range: -1.5264

Max Act: 1.2151. Min Act: -0.0002

Data Index: 790284 (C4 (Web Text))

Max Activating Token Index: 675

Text #6

Max Range: 1.5264. Min Range: -1.5264

Max Act: 1.2779. Min Act: -0.0002

Data Index: 753126 (C4 (Web Text))

Max Activating Token Index: 268

Text #7

Max Range: 1.5264. Min Range: -1.5264

Max Act: 1.2386. Min Act: -0.0002

Data Index: 672310 (C4 (Web Text))

Max Activating Token Index: 281

Text #8

Max Range: 1.5264. Min Range: -1.5264

Max Act: 1.2424. Min Act: -0.0002

Data Index: 264458 (C4 (Web Text))

Max Activating Token Index: 81

Text #9

Max Range: 1.5264. Min Range: -1.5264

Max Act: 1.1917. Min Act: -0.0002

Data Index: 675877 (C4 (Web Text))

Max Activating Token Index: 486

Text #10

Max Range: 1.5264. Min Range: -1.5264

Max Act: 1.2452. Min Act: -0.0003

Data Index: 1098382 (C4 (Web Text))

Max Activating Token Index: 39

Text #11

Max Range: 1.5264. Min Range: -1.5264

Max Act: 1.1703. Min Act: -0.0002

Data Index: 58764 (C4 (Web Text))

Max Activating Token Index: 46

Text #12

Max Range: 1.5264. Min Range: -1.5264

Max Act: 1.1602. Min Act: -0.0002

Data Index: 1027984 (C4 (Web Text))

Max Activating Token Index: 233

Text #13

Max Range: 1.5264. Min Range: -1.5264

Max Act: 1.1923. Min Act: -0.0002

Data Index: 842359 (C4 (Web Text))

Max Activating Token Index: 728

Text #14

Max Range: 1.5264. Min Range: -1.5264

Max Act: 1.2668. Min Act: -0.0003

Data Index: 105222 (C4 (Web Text))

Max Activating Token Index: 732

Text #15

Max Range: 1.5264. Min Range: -1.5264

Max Act: 1.1916. Min Act: -0.0003

Data Index: 674878 (C4 (Web Text))

Max Activating Token Index: 298

Text #16

Max Range: 1.5264. Min Range: -1.5264

Max Act: 1.1138. Min Act: -0.0002

Data Index: 1096072 (C4 (Web Text))

Max Activating Token Index: 74

Text #17

Max Range: 1.5264. Min Range: -1.5264

Max Act: 1.1629. Min Act: -0.0002

Data Index: 1124587 (C4 (Web Text))

Max Activating Token Index: 50

Text #18

Max Range: 1.5264. Min Range: -1.5264

Max Act: 1.1665. Min Act: -0.0002

Data Index: 602945 (C4 (Web Text))

Max Activating Token Index: 45

Text #19

Max Range: 1.5264. Min Range: -1.5264

Max Act: 1.1348. Min Act: -0.0002

Data Index: 577311 (C4 (Web Text))

Max Activating Token Index: 438