Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2979 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.1216. Min Act: -0.0001

Data Index: 350495 (C4 (Web Text))

Max Activating Token Index: 338

Text #1

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.1000. Min Act: -0.0001

Data Index: 1239368 (C4 (Web Text))

Max Activating Token Index: 387

Text #2

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.1025. Min Act: -0.0001

Data Index: 660765 (C4 (Web Text))

Max Activating Token Index: 883

Text #3

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.1043. Min Act: -0.0001

Data Index: 1069959 (C4 (Web Text))

Max Activating Token Index: 430

Text #4

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.1024. Min Act: -0.0001

Data Index: 740847 (C4 (Web Text))

Max Activating Token Index: 396

Text #5

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.0955. Min Act: -0.0001

Data Index: 1646 (C4 (Web Text))

Max Activating Token Index: 188

Text #6

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.0955. Min Act: -0.0001

Data Index: 1117430 (C4 (Web Text))

Max Activating Token Index: 880

Text #7

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.1024. Min Act: -0.0001

Data Index: 1134496 (C4 (Web Text))

Max Activating Token Index: 301

Text #8

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.0980. Min Act: -0.0001

Data Index: 925434 (C4 (Web Text))

Max Activating Token Index: 659

Text #9

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.1010. Min Act: -0.0001

Data Index: 925078 (C4 (Web Text))

Max Activating Token Index: 801

Text #10

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.0975. Min Act: -0.0001

Data Index: 206900 (C4 (Web Text))

Max Activating Token Index: 486

Text #11

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.0953. Min Act: -0.0001

Data Index: 549681 (C4 (Web Text))

Max Activating Token Index: 990

Text #12

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.0971. Min Act: -0.0001

Data Index: 4647 (C4 (Web Text))

Max Activating Token Index: 272

Text #13

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.0901. Min Act: -0.0001

Data Index: 1178259 (C4 (Web Text))

Max Activating Token Index: 809

Text #14

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.0904. Min Act: -0.0001

Data Index: 290649 (C4 (Web Text))

Max Activating Token Index: 352

Text #15

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.0955. Min Act: -0.0001

Data Index: 291169 (C4 (Web Text))

Max Activating Token Index: 315

Text #16

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.0894. Min Act: -0.0001

Data Index: 342516 (C4 (Web Text))

Max Activating Token Index: 250

Text #17

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.0844. Min Act: -0.0001

Data Index: 290189 (C4 (Web Text))

Max Activating Token Index: 235

Text #18

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.0906. Min Act: -0.0001

Data Index: 1195219 (C4 (Web Text))

Max Activating Token Index: 476

Text #19

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.0902. Min Act: -0.0001

Data Index: 998711 (C4 (Web Text))

Max Activating Token Index: 506