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

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

Neuron 1620 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5950. Min Range: -3.5950

Max Act: 3.4635. Min Act: -0.0001

Data Index: 1092455 (C4 (Web Text))

Max Activating Token Index: 57

Text #1

Max Range: 3.5950. Min Range: -3.5950

Max Act: 3.5950. Min Act: -0.0001

Data Index: 917227 (C4 (Web Text))

Max Activating Token Index: 140

Text #2

Max Range: 3.5950. Min Range: -3.5950

Max Act: 3.1997. Min Act: -0.0001

Data Index: 666736 (C4 (Web Text))

Max Activating Token Index: 199

Text #3

Max Range: 3.5950. Min Range: -3.5950

Max Act: 3.1545. Min Act: -0.0001

Data Index: 258914 (C4 (Web Text))

Max Activating Token Index: 13

Text #4

Max Range: 3.5950. Min Range: -3.5950

Max Act: 3.4474. Min Act: -0.0001

Data Index: 681684 (C4 (Web Text))

Max Activating Token Index: 445

Text #5

Max Range: 3.5950. Min Range: -3.5950

Max Act: 3.0891. Min Act: -0.0001

Data Index: 650368 (C4 (Web Text))

Max Activating Token Index: 320

Text #6

Max Range: 3.5950. Min Range: -3.5950

Max Act: 3.0359. Min Act: -0.0001

Data Index: 903861 (C4 (Web Text))

Max Activating Token Index: 414

Text #7

Max Range: 3.5950. Min Range: -3.5950

Max Act: 3.1697. Min Act: -0.0001

Data Index: 759505 (C4 (Web Text))

Max Activating Token Index: 219

Text #8

Max Range: 3.5950. Min Range: -3.5950

Max Act: 3.2932. Min Act: -0.0001

Data Index: 990585 (C4 (Web Text))

Max Activating Token Index: 680

Text #9

Max Range: 3.5950. Min Range: -3.5950

Max Act: 3.1622. Min Act: -0.0001

Data Index: 588767 (C4 (Web Text))

Max Activating Token Index: 293

Text #10

Max Range: 3.5950. Min Range: -3.5950

Max Act: 3.0097. Min Act: -0.0001

Data Index: 815701 (C4 (Web Text))

Max Activating Token Index: 456

Text #11

Max Range: 3.5950. Min Range: -3.5950

Max Act: 2.8600. Min Act: -0.0001

Data Index: 1073133 (C4 (Web Text))

Max Activating Token Index: 259

Text #12

Max Range: 3.5950. Min Range: -3.5950

Max Act: 2.8860. Min Act: -0.0001

Data Index: 1183101 (C4 (Web Text))

Max Activating Token Index: 259

Text #13

Max Range: 3.5950. Min Range: -3.5950

Max Act: 2.8654. Min Act: -0.0001

Data Index: 922890 (C4 (Web Text))

Max Activating Token Index: 205

Text #14

Max Range: 3.5950. Min Range: -3.5950

Max Act: 3.3142. Min Act: -0.0001

Data Index: 105877 (C4 (Web Text))

Max Activating Token Index: 249

Text #15

Max Range: 3.5950. Min Range: -3.5950

Max Act: 2.9798. Min Act: -0.0001

Data Index: 203841 (C4 (Web Text))

Max Activating Token Index: 26

Text #16

Max Range: 3.5950. Min Range: -3.5950

Max Act: 2.8122. Min Act: -0.0001

Data Index: 437527 (C4 (Web Text))

Max Activating Token Index: 950

Text #17

Max Range: 3.5950. Min Range: -3.5950

Max Act: 2.8823. Min Act: -0.0001

Data Index: 232912 (C4 (Web Text))

Max Activating Token Index: 214

Text #18

Max Range: 3.5950. Min Range: -3.5950

Max Act: 2.8636. Min Act: -0.0001

Data Index: 757179 (C4 (Web Text))

Max Activating Token Index: 171

Text #19

Max Range: 3.5950. Min Range: -3.5950

Max Act: 3.1497. Min Act: -0.0001

Data Index: 984029 (C4 (Web Text))

Max Activating Token Index: 154