Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1601 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0035. Min Act: -0.0005

Data Index: 96144 (C4 (Web Text))

Max Activating Token Index: 65

Text #1

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0034. Min Act: -0.0005

Data Index: 1120456 (C4 (Web Text))

Max Activating Token Index: 728

Text #2

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0033. Min Act: -0.0005

Data Index: 314268 (C4 (Web Text))

Max Activating Token Index: 728

Text #3

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0032. Min Act: -0.0005

Data Index: 1137864 (C4 (Web Text))

Max Activating Token Index: 676

Text #4

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0032. Min Act: -0.0005

Data Index: 257327 (C4 (Web Text))

Max Activating Token Index: 537

Text #5

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0032. Min Act: -0.0005

Data Index: 1022503 (C4 (Web Text))

Max Activating Token Index: 537

Text #6

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0031. Min Act: -0.0005

Data Index: 1157685 (C4 (Web Text))

Max Activating Token Index: 219

Text #7

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0031. Min Act: -0.0005

Data Index: 414227 (C4 (Web Text))

Max Activating Token Index: 496

Text #8

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0031. Min Act: -0.0005

Data Index: 92578 (C4 (Web Text))

Max Activating Token Index: 614

Text #9

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0031. Min Act: -0.0005

Data Index: 18437 (C4 (Web Text))

Max Activating Token Index: 614

Text #10

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0031. Min Act: -0.0005

Data Index: 813021 (C4 (Web Text))

Max Activating Token Index: 614

Text #11

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0031. Min Act: -0.0005

Data Index: 482964 (C4 (Web Text))

Max Activating Token Index: 610

Text #12

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0031. Min Act: -0.0005

Data Index: 1321759 (C4 (Web Text))

Max Activating Token Index: 614

Text #13

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0031. Min Act: -0.0005

Data Index: 401374 (C4 (Web Text))

Max Activating Token Index: 703

Text #14

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0030. Min Act: -0.0005

Data Index: 1159482 (C4 (Web Text))

Max Activating Token Index: 65

Text #15

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0030. Min Act: -0.0004

Data Index: 1382997 (Python Code)

Max Activating Token Index: 978

Text #16

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0030. Min Act: -0.0005

Data Index: 754754 (C4 (Web Text))

Max Activating Token Index: 219

Text #17

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0030. Min Act: -0.0005

Data Index: 466685 (C4 (Web Text))

Max Activating Token Index: 146

Text #18

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0030. Min Act: -0.0005

Data Index: 320619 (C4 (Web Text))

Max Activating Token Index: 235

Text #19

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0030. Min Act: -0.0005

Data Index: 1170654 (C4 (Web Text))

Max Activating Token Index: 496