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

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

Neuron 3916 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1191. Min Range: -0.1191

Max Act: 0.1191. Min Act: -0.0002

Data Index: 618190 (C4 (Web Text))

Max Activating Token Index: 221

Text #1

Max Range: 0.1191. Min Range: -0.1191

Max Act: 0.0890. Min Act: -0.0002

Data Index: 1122108 (C4 (Web Text))

Max Activating Token Index: 293

Text #2

Max Range: 0.1191. Min Range: -0.1191

Max Act: 0.0860. Min Act: -0.0002

Data Index: 362703 (C4 (Web Text))

Max Activating Token Index: 163

Text #3

Max Range: 0.1191. Min Range: -0.1191

Max Act: 0.0900. Min Act: -0.0002

Data Index: 1598040 (Python Code)

Max Activating Token Index: 163

Text #4

Max Range: 0.1191. Min Range: -0.1191

Max Act: 0.0819. Min Act: -0.0002

Data Index: 1349051 (C4 (Web Text))

Max Activating Token Index: 644

Text #5

Max Range: 0.1191. Min Range: -0.1191

Max Act: 0.0898. Min Act: -0.0002

Data Index: 858020 (C4 (Web Text))

Max Activating Token Index: 781

Text #6

Max Range: 0.1191. Min Range: -0.1191

Max Act: 0.0840. Min Act: -0.0002

Data Index: 841634 (C4 (Web Text))

Max Activating Token Index: 2

Text #7

Max Range: 0.1191. Min Range: -0.1191

Max Act: 0.0839. Min Act: -0.0002

Data Index: 1520020 (Python Code)

Max Activating Token Index: 1004

Text #8

Max Range: 0.1191. Min Range: -0.1191

Max Act: 0.0762. Min Act: -0.0002

Data Index: 1521489 (Python Code)

Max Activating Token Index: 339

Text #9

Max Range: 0.1191. Min Range: -0.1191

Max Act: 0.0769. Min Act: -0.0002

Data Index: 491668 (C4 (Web Text))

Max Activating Token Index: 1

Text #10

Max Range: 0.1191. Min Range: -0.1191

Max Act: 0.0769. Min Act: -0.0002

Data Index: 1166014 (C4 (Web Text))

Max Activating Token Index: 1

Text #11

Max Range: 0.1191. Min Range: -0.1191

Max Act: 0.0787. Min Act: -0.0002

Data Index: 1605047 (Python Code)

Max Activating Token Index: 98

Text #12

Max Range: 0.1191. Min Range: -0.1191

Max Act: 0.0762. Min Act: -0.0002

Data Index: 1637640 (Python Code)

Max Activating Token Index: 520

Text #13

Max Range: 0.1191. Min Range: -0.1191

Max Act: 0.0780. Min Act: -0.0002

Data Index: 1163271 (C4 (Web Text))

Max Activating Token Index: 465

Text #14

Max Range: 0.1191. Min Range: -0.1191

Max Act: 0.0794. Min Act: -0.0002

Data Index: 359033 (C4 (Web Text))

Max Activating Token Index: 794

Text #15

Max Range: 0.1191. Min Range: -0.1191

Max Act: 0.0763. Min Act: -0.0002

Data Index: 322161 (C4 (Web Text))

Max Activating Token Index: 1

Text #16

Max Range: 0.1191. Min Range: -0.1191

Max Act: 0.0755. Min Act: -0.0002

Data Index: 960483 (C4 (Web Text))

Max Activating Token Index: 524

Text #17

Max Range: 0.1191. Min Range: -0.1191

Max Act: 0.0752. Min Act: -0.0002

Data Index: 1416856 (Python Code)

Max Activating Token Index: 2

Text #18

Max Range: 0.1191. Min Range: -0.1191

Max Act: 0.0727. Min Act: -0.0002

Data Index: 766598 (C4 (Web Text))

Max Activating Token Index: 522

Text #19

Max Range: 0.1191. Min Range: -0.1191

Max Act: 0.0770. Min Act: -0.0002

Data Index: 494978 (C4 (Web Text))

Max Activating Token Index: 921