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

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

Neuron 3087 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7742. Min Range: -0.7742

Max Act: 0.7742. Min Act: -0.0001

Data Index: 1158449 (C4 (Web Text))

Max Activating Token Index: 43

Text #1

Max Range: 0.7742. Min Range: -0.7742

Max Act: 0.7077. Min Act: -0.0001

Data Index: 1060569 (C4 (Web Text))

Max Activating Token Index: 836

Text #2

Max Range: 0.7742. Min Range: -0.7742

Max Act: 0.6931. Min Act: -0.0001

Data Index: 894491 (C4 (Web Text))

Max Activating Token Index: 862

Text #3

Max Range: 0.7742. Min Range: -0.7742

Max Act: 0.4370. Min Act: -0.0001

Data Index: 61188 (C4 (Web Text))

Max Activating Token Index: 288

Text #4

Max Range: 0.7742. Min Range: -0.7742

Max Act: 0.6132. Min Act: -0.0001

Data Index: 784597 (C4 (Web Text))

Max Activating Token Index: 127

Text #5

Max Range: 0.7742. Min Range: -0.7742

Max Act: 0.5881. Min Act: -0.0001

Data Index: 312402 (C4 (Web Text))

Max Activating Token Index: 171

Text #6

Max Range: 0.7742. Min Range: -0.7742

Max Act: 0.6783. Min Act: -0.0001

Data Index: 251759 (C4 (Web Text))

Max Activating Token Index: 779

Text #7

Max Range: 0.7742. Min Range: -0.7742

Max Act: 0.6467. Min Act: -0.0001

Data Index: 1249787 (C4 (Web Text))

Max Activating Token Index: 16

Text #8

Max Range: 0.7742. Min Range: -0.7742

Max Act: 0.5330. Min Act: -0.0001

Data Index: 211416 (C4 (Web Text))

Max Activating Token Index: 357

Text #9

Max Range: 0.7742. Min Range: -0.7742

Max Act: 0.6095. Min Act: -0.0001

Data Index: 1031461 (C4 (Web Text))

Max Activating Token Index: 957

Text #10

Max Range: 0.7742. Min Range: -0.7742

Max Act: 0.6261. Min Act: -0.0001

Data Index: 956777 (C4 (Web Text))

Max Activating Token Index: 309

Text #11

Max Range: 0.7742. Min Range: -0.7742

Max Act: 0.5666. Min Act: -0.0001

Data Index: 1107004 (C4 (Web Text))

Max Activating Token Index: 875

Text #12

Max Range: 0.7742. Min Range: -0.7742

Max Act: 0.6007. Min Act: -0.0001

Data Index: 1273042 (C4 (Web Text))

Max Activating Token Index: 195

Text #13

Max Range: 0.7742. Min Range: -0.7742

Max Act: 0.5775. Min Act: -0.0001

Data Index: 131071 (C4 (Web Text))

Max Activating Token Index: 7

Text #14

Max Range: 0.7742. Min Range: -0.7742

Max Act: 0.5689. Min Act: -0.0001

Data Index: 1257928 (C4 (Web Text))

Max Activating Token Index: 41

Text #15

Max Range: 0.7742. Min Range: -0.7742

Max Act: 0.5879. Min Act: -0.0001

Data Index: 706446 (C4 (Web Text))

Max Activating Token Index: 590

Text #16

Max Range: 0.7742. Min Range: -0.7742

Max Act: 0.5983. Min Act: -0.0001

Data Index: 270523 (C4 (Web Text))

Max Activating Token Index: 694

Text #17

Max Range: 0.7742. Min Range: -0.7742

Max Act: 0.3780. Min Act: -0.0001

Data Index: 1010108 (C4 (Web Text))

Max Activating Token Index: 66

Text #18

Max Range: 0.7742. Min Range: -0.7742

Max Act: 0.5569. Min Act: -0.0001

Data Index: 344212 (C4 (Web Text))

Max Activating Token Index: 55

Text #19

Max Range: 0.7742. Min Range: -0.7742

Max Act: 0.6272. Min Act: -0.0001

Data Index: 294619 (C4 (Web Text))

Max Activating Token Index: 350