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

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

Neuron 4431 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: 0.9331. Min Range: -0.9331

Max Act: 0.9331. Min Act: -0.0000

Data Index: 1257446 (C4 (Web Text))

Max Activating Token Index: 167

Text #1

Max Range: 0.9331. Min Range: -0.9331

Max Act: 0.7383. Min Act: -0.0000

Data Index: 921914 (C4 (Web Text))

Max Activating Token Index: 222

Text #2

Max Range: 0.9331. Min Range: -0.9331

Max Act: 0.7125. Min Act: -0.0000

Data Index: 603138 (C4 (Web Text))

Max Activating Token Index: 403

Text #3

Max Range: 0.9331. Min Range: -0.9331

Max Act: 0.6084. Min Act: -0.0000

Data Index: 673680 (C4 (Web Text))

Max Activating Token Index: 865

Text #4

Max Range: 0.9331. Min Range: -0.9331

Max Act: 0.6063. Min Act: -0.0000

Data Index: 306132 (C4 (Web Text))

Max Activating Token Index: 1003

Text #5

Max Range: 0.9331. Min Range: -0.9331

Max Act: 0.5354. Min Act: -0.0000

Data Index: 1157114 (C4 (Web Text))

Max Activating Token Index: 199

Text #6

Max Range: 0.9331. Min Range: -0.9331

Max Act: 0.6735. Min Act: -0.0000

Data Index: 1254318 (C4 (Web Text))

Max Activating Token Index: 687

Text #7

Max Range: 0.9331. Min Range: -0.9331

Max Act: 0.6239. Min Act: -0.0000

Data Index: 90673 (C4 (Web Text))

Max Activating Token Index: 752

Text #8

Max Range: 0.9331. Min Range: -0.9331

Max Act: 0.6360. Min Act: -0.0000

Data Index: 1066846 (C4 (Web Text))

Max Activating Token Index: 821

Text #9

Max Range: 0.9331. Min Range: -0.9331

Max Act: 0.6024. Min Act: -0.0001

Data Index: 1344529 (C4 (Web Text))

Max Activating Token Index: 110

Text #10

Max Range: 0.9331. Min Range: -0.9331

Max Act: 0.6309. Min Act: -0.0000

Data Index: 929572 (C4 (Web Text))

Max Activating Token Index: 309

Text #11

Max Range: 0.9331. Min Range: -0.9331

Max Act: 0.5368. Min Act: -0.0000

Data Index: 202130 (C4 (Web Text))

Max Activating Token Index: 43

Text #12

Max Range: 0.9331. Min Range: -0.9331

Max Act: 0.5595. Min Act: -0.0001

Data Index: 814988 (C4 (Web Text))

Max Activating Token Index: 511

Text #13

Max Range: 0.9331. Min Range: -0.9331

Max Act: 0.5792. Min Act: -0.0000

Data Index: 1265845 (C4 (Web Text))

Max Activating Token Index: 801

Text #14

Max Range: 0.9331. Min Range: -0.9331

Max Act: 0.5726. Min Act: -0.0000

Data Index: 1258027 (C4 (Web Text))

Max Activating Token Index: 821

Text #15

Max Range: 0.9331. Min Range: -0.9331

Max Act: 0.5661. Min Act: -0.0000

Data Index: 84484 (C4 (Web Text))

Max Activating Token Index: 235

Text #16

Max Range: 0.9331. Min Range: -0.9331

Max Act: 0.5335. Min Act: -0.0000

Data Index: 987087 (C4 (Web Text))

Max Activating Token Index: 504

Text #17

Max Range: 0.9331. Min Range: -0.9331

Max Act: 0.5817. Min Act: -0.0001

Data Index: 1356172 (C4 (Web Text))

Max Activating Token Index: 820

Text #18

Max Range: 0.9331. Min Range: -0.9331

Max Act: 0.4528. Min Act: -0.0000

Data Index: 92249 (C4 (Web Text))

Max Activating Token Index: 188

Text #19

Max Range: 0.9331. Min Range: -0.9331

Max Act: 0.5134. Min Act: -0.0000

Data Index: 786642 (C4 (Web Text))

Max Activating Token Index: 501