Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1632 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.1105. Min Act: -0.0003

Data Index: 455598 (C4 (Web Text))

Max Activating Token Index: 985

Text #1

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.1006. Min Act: -0.0002

Data Index: 889356 (C4 (Web Text))

Max Activating Token Index: 73

Text #2

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0959. Min Act: -0.0003

Data Index: 446500 (C4 (Web Text))

Max Activating Token Index: 301

Text #3

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0820. Min Act: -0.0003

Data Index: 774752 (C4 (Web Text))

Max Activating Token Index: 604

Text #4

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0813. Min Act: -0.0003

Data Index: 885117 (C4 (Web Text))

Max Activating Token Index: 674

Text #5

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0843. Min Act: -0.0003

Data Index: 591112 (C4 (Web Text))

Max Activating Token Index: 293

Text #6

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0795. Min Act: -0.0003

Data Index: 768870 (C4 (Web Text))

Max Activating Token Index: 43

Text #7

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0773. Min Act: -0.0003

Data Index: 992820 (C4 (Web Text))

Max Activating Token Index: 151

Text #8

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0761. Min Act: -0.0003

Data Index: 613289 (C4 (Web Text))

Max Activating Token Index: 126

Text #9

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0768. Min Act: -0.0003

Data Index: 106195 (C4 (Web Text))

Max Activating Token Index: 844

Text #10

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0758. Min Act: -0.0003

Data Index: 1615859 (Python Code)

Max Activating Token Index: 109

Text #11

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0755. Min Act: -0.0003

Data Index: 707048 (C4 (Web Text))

Max Activating Token Index: 789

Text #12

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0783. Min Act: -0.0003

Data Index: 740000 (C4 (Web Text))

Max Activating Token Index: 953

Text #13

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0766. Min Act: -0.0002

Data Index: 166111 (C4 (Web Text))

Max Activating Token Index: 92

Text #14

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0749. Min Act: -0.0003

Data Index: 566224 (C4 (Web Text))

Max Activating Token Index: 511

Text #15

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0750. Min Act: -0.0003

Data Index: 1062730 (C4 (Web Text))

Max Activating Token Index: 702

Text #16

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0738. Min Act: -0.0003

Data Index: 1044731 (C4 (Web Text))

Max Activating Token Index: 21

Text #17

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0749. Min Act: -0.0003

Data Index: 1273726 (C4 (Web Text))

Max Activating Token Index: 391

Text #18

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0722. Min Act: -0.0003

Data Index: 304231 (C4 (Web Text))

Max Activating Token Index: 452

Text #19

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0740. Min Act: -0.0003

Data Index: 1601542 (Python Code)

Max Activating Token Index: 495