Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5040 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6719. Min Range: -0.6719

Max Act: 0.5922. Min Act: -0.0002

Data Index: 1131659 (C4 (Web Text))

Max Activating Token Index: 687

Text #1

Max Range: 0.6719. Min Range: -0.6719

Max Act: 0.5731. Min Act: -0.0001

Data Index: 391705 (C4 (Web Text))

Max Activating Token Index: 359

Text #2

Max Range: 0.6719. Min Range: -0.6719

Max Act: 0.6190. Min Act: -0.0001

Data Index: 710137 (C4 (Web Text))

Max Activating Token Index: 192

Text #3

Max Range: 0.6719. Min Range: -0.6719

Max Act: 0.6716. Min Act: -0.0002

Data Index: 743562 (C4 (Web Text))

Max Activating Token Index: 656

Text #4

Max Range: 0.6719. Min Range: -0.6719

Max Act: 0.6719. Min Act: -0.0001

Data Index: 1264550 (C4 (Web Text))

Max Activating Token Index: 224

Text #5

Max Range: 0.6719. Min Range: -0.6719

Max Act: 0.6011. Min Act: -0.0002

Data Index: 159600 (C4 (Web Text))

Max Activating Token Index: 128

Text #6

Max Range: 0.6719. Min Range: -0.6719

Max Act: 0.5465. Min Act: -0.0001

Data Index: 1300886 (C4 (Web Text))

Max Activating Token Index: 5

Text #7

Max Range: 0.6719. Min Range: -0.6719

Max Act: 0.5875. Min Act: -0.0001

Data Index: 91520 (C4 (Web Text))

Max Activating Token Index: 124

Text #8

Max Range: 0.6719. Min Range: -0.6719

Max Act: 0.5587. Min Act: -0.0001

Data Index: 1009161 (C4 (Web Text))

Max Activating Token Index: 161

Text #9

Max Range: 0.6719. Min Range: -0.6719

Max Act: 0.5626. Min Act: -0.0001

Data Index: 333385 (C4 (Web Text))

Max Activating Token Index: 3

Text #10

Max Range: 0.6719. Min Range: -0.6719

Max Act: 0.5898. Min Act: -0.0001

Data Index: 1222517 (C4 (Web Text))

Max Activating Token Index: 228

Text #11

Max Range: 0.6719. Min Range: -0.6719

Max Act: 0.5745. Min Act: -0.0001

Data Index: 878317 (C4 (Web Text))

Max Activating Token Index: 97

Text #12

Max Range: 0.6719. Min Range: -0.6719

Max Act: 0.5573. Min Act: -0.0001

Data Index: 900192 (C4 (Web Text))

Max Activating Token Index: 234

Text #13

Max Range: 0.6719. Min Range: -0.6719

Max Act: 0.5816. Min Act: -0.0001

Data Index: 1269199 (C4 (Web Text))

Max Activating Token Index: 831

Text #14

Max Range: 0.6719. Min Range: -0.6719

Max Act: 0.6083. Min Act: -0.0002

Data Index: 1166647 (C4 (Web Text))

Max Activating Token Index: 138

Text #15

Max Range: 0.6719. Min Range: -0.6719

Max Act: 0.6658. Min Act: -0.0001

Data Index: 539266 (C4 (Web Text))

Max Activating Token Index: 220

Text #16

Max Range: 0.6719. Min Range: -0.6719

Max Act: 0.5474. Min Act: -0.0001

Data Index: 1070233 (C4 (Web Text))

Max Activating Token Index: 16

Text #17

Max Range: 0.6719. Min Range: -0.6719

Max Act: 0.5921. Min Act: -0.0001

Data Index: 1055691 (C4 (Web Text))

Max Activating Token Index: 333

Text #18

Max Range: 0.6719. Min Range: -0.6719

Max Act: 0.5907. Min Act: -0.0001

Data Index: 22640 (C4 (Web Text))

Max Activating Token Index: 298

Text #19

Max Range: 0.6719. Min Range: -0.6719

Max Act: 0.5442. Min Act: -0.0001

Data Index: 348317 (C4 (Web Text))

Max Activating Token Index: 2