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

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

Neuron 4137 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.2090. Min Act: -0.0001

Data Index: 983364 (C4 (Web Text))

Max Activating Token Index: 224

Text #1

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.2219. Min Act: -0.0001

Data Index: 275790 (C4 (Web Text))

Max Activating Token Index: 328

Text #2

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.2162. Min Act: -0.0001

Data Index: 622114 (C4 (Web Text))

Max Activating Token Index: 105

Text #3

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.2132. Min Act: -0.0001

Data Index: 680184 (C4 (Web Text))

Max Activating Token Index: 488

Text #4

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.2084. Min Act: -0.0001

Data Index: 1010704 (C4 (Web Text))

Max Activating Token Index: 952

Text #5

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1894. Min Act: -0.0001

Data Index: 850672 (C4 (Web Text))

Max Activating Token Index: 162

Text #6

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1980. Min Act: -0.0001

Data Index: 13508 (C4 (Web Text))

Max Activating Token Index: 596

Text #7

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.2117. Min Act: -0.0001

Data Index: 564230 (C4 (Web Text))

Max Activating Token Index: 559

Text #8

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1953. Min Act: -0.0001

Data Index: 241613 (C4 (Web Text))

Max Activating Token Index: 134

Text #9

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.2067. Min Act: -0.0001

Data Index: 526176 (C4 (Web Text))

Max Activating Token Index: 192

Text #10

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.2009. Min Act: -0.0001

Data Index: 555259 (C4 (Web Text))

Max Activating Token Index: 390

Text #11

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1939. Min Act: -0.0001

Data Index: 199876 (C4 (Web Text))

Max Activating Token Index: 468

Text #12

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.2029. Min Act: -0.0001

Data Index: 14662 (C4 (Web Text))

Max Activating Token Index: 66

Text #13

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1813. Min Act: -0.0001

Data Index: 608288 (C4 (Web Text))

Max Activating Token Index: 253

Text #14

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1728. Min Act: -0.0001

Data Index: 383553 (C4 (Web Text))

Max Activating Token Index: 212

Text #15

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1795. Min Act: -0.0001

Data Index: 4738 (C4 (Web Text))

Max Activating Token Index: 267

Text #16

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1906. Min Act: -0.0001

Data Index: 906104 (C4 (Web Text))

Max Activating Token Index: 357

Text #17

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.2121. Min Act: -0.0001

Data Index: 910401 (C4 (Web Text))

Max Activating Token Index: 808

Text #18

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1758. Min Act: -0.0001

Data Index: 843202 (C4 (Web Text))

Max Activating Token Index: 528

Text #19

Max Range: 0.2219. Min Range: -0.2219

Max Act: 0.1707. Min Act: -0.0001

Data Index: 1145556 (C4 (Web Text))

Max Activating Token Index: 583