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

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

Neuron 3638 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4819. Min Range: -0.4819

Max Act: 0.4819. Min Act: -0.0000

Data Index: 1300498 (C4 (Web Text))

Max Activating Token Index: 400

Text #1

Max Range: 0.4819. Min Range: -0.4819

Max Act: 0.4521. Min Act: -0.0000

Data Index: 1143529 (C4 (Web Text))

Max Activating Token Index: 275

Text #2

Max Range: 0.4819. Min Range: -0.4819

Max Act: 0.4268. Min Act: -0.0000

Data Index: 1106387 (C4 (Web Text))

Max Activating Token Index: 502

Text #3

Max Range: 0.4819. Min Range: -0.4819

Max Act: 0.4243. Min Act: -0.0000

Data Index: 1104650 (C4 (Web Text))

Max Activating Token Index: 931

Text #4

Max Range: 0.4819. Min Range: -0.4819

Max Act: 0.4358. Min Act: -0.0000

Data Index: 97719 (C4 (Web Text))

Max Activating Token Index: 264

Text #5

Max Range: 0.4819. Min Range: -0.4819

Max Act: 0.4095. Min Act: -0.0000

Data Index: 1115477 (C4 (Web Text))

Max Activating Token Index: 5

Text #6

Max Range: 0.4819. Min Range: -0.4819

Max Act: 0.3968. Min Act: -0.0000

Data Index: 918550 (C4 (Web Text))

Max Activating Token Index: 285

Text #7

Max Range: 0.4819. Min Range: -0.4819

Max Act: 0.4145. Min Act: -0.0000

Data Index: 80435 (C4 (Web Text))

Max Activating Token Index: 268

Text #8

Max Range: 0.4819. Min Range: -0.4819

Max Act: 0.3931. Min Act: -0.0000

Data Index: 1263310 (C4 (Web Text))

Max Activating Token Index: 51

Text #9

Max Range: 0.4819. Min Range: -0.4819

Max Act: 0.4154. Min Act: -0.0000

Data Index: 330661 (C4 (Web Text))

Max Activating Token Index: 183

Text #10

Max Range: 0.4819. Min Range: -0.4819

Max Act: 0.4053. Min Act: -0.0000

Data Index: 168606 (C4 (Web Text))

Max Activating Token Index: 165

Text #11

Max Range: 0.4819. Min Range: -0.4819

Max Act: 0.4133. Min Act: -0.0000

Data Index: 125707 (C4 (Web Text))

Max Activating Token Index: 298

Text #12

Max Range: 0.4819. Min Range: -0.4819

Max Act: 0.3954. Min Act: -0.0000

Data Index: 105692 (C4 (Web Text))

Max Activating Token Index: 645

Text #13

Max Range: 0.4819. Min Range: -0.4819

Max Act: 0.3909. Min Act: -0.0000

Data Index: 1225042 (C4 (Web Text))

Max Activating Token Index: 14

Text #14

Max Range: 0.4819. Min Range: -0.4819

Max Act: 0.3670. Min Act: -0.0000

Data Index: 721249 (C4 (Web Text))

Max Activating Token Index: 265

Text #15

Max Range: 0.4819. Min Range: -0.4819

Max Act: 0.3834. Min Act: -0.0000

Data Index: 584167 (C4 (Web Text))

Max Activating Token Index: 753

Text #16

Max Range: 0.4819. Min Range: -0.4819

Max Act: 0.3751. Min Act: -0.0000

Data Index: 351214 (C4 (Web Text))

Max Activating Token Index: 251

Text #17

Max Range: 0.4819. Min Range: -0.4819

Max Act: 0.3890. Min Act: -0.0000

Data Index: 1050409 (C4 (Web Text))

Max Activating Token Index: 687

Text #18

Max Range: 0.4819. Min Range: -0.4819

Max Act: 0.3757. Min Act: -0.0000

Data Index: 163480 (C4 (Web Text))

Max Activating Token Index: 250

Text #19

Max Range: 0.4819. Min Range: -0.4819

Max Act: 0.3723. Min Act: -0.0000

Data Index: 872677 (C4 (Web Text))

Max Activating Token Index: 885