Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2324 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.1298. Min Act: -0.0001

Data Index: 280041 (C4 (Web Text))

Max Activating Token Index: 92

Text #1

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.1112. Min Act: -0.0000

Data Index: 990060 (C4 (Web Text))

Max Activating Token Index: 970

Text #2

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.1010. Min Act: -0.0001

Data Index: 950173 (C4 (Web Text))

Max Activating Token Index: 430

Text #3

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.0907. Min Act: -0.0001

Data Index: 1282584 (C4 (Web Text))

Max Activating Token Index: 95

Text #4

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.0963. Min Act: -0.0001

Data Index: 975845 (C4 (Web Text))

Max Activating Token Index: 889

Text #5

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.1005. Min Act: -0.0000

Data Index: 1308852 (C4 (Web Text))

Max Activating Token Index: 577

Text #6

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.0961. Min Act: -0.0001

Data Index: 144531 (C4 (Web Text))

Max Activating Token Index: 224

Text #7

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.0876. Min Act: -0.0001

Data Index: 614311 (C4 (Web Text))

Max Activating Token Index: 441

Text #8

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.0904. Min Act: -0.0001

Data Index: 842565 (C4 (Web Text))

Max Activating Token Index: 341

Text #9

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.0935. Min Act: -0.0000

Data Index: 872400 (C4 (Web Text))

Max Activating Token Index: 629

Text #10

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.0867. Min Act: -0.0000

Data Index: 952816 (C4 (Web Text))

Max Activating Token Index: 441

Text #11

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.0848. Min Act: -0.0001

Data Index: 686898 (C4 (Web Text))

Max Activating Token Index: 263

Text #12

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.0864. Min Act: -0.0001

Data Index: 53213 (C4 (Web Text))

Max Activating Token Index: 146

Text #13

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.0870. Min Act: -0.0001

Data Index: 968523 (C4 (Web Text))

Max Activating Token Index: 478

Text #14

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.0765. Min Act: -0.0001

Data Index: 204789 (C4 (Web Text))

Max Activating Token Index: 774

Text #15

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.0864. Min Act: -0.0001

Data Index: 83433 (C4 (Web Text))

Max Activating Token Index: 750

Text #16

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.0823. Min Act: -0.0001

Data Index: 453630 (C4 (Web Text))

Max Activating Token Index: 213

Text #17

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.0767. Min Act: -0.0001

Data Index: 1308848 (C4 (Web Text))

Max Activating Token Index: 507

Text #18

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.0794. Min Act: -0.0001

Data Index: 1314778 (C4 (Web Text))

Max Activating Token Index: 520

Text #19

Max Range: 0.1298. Min Range: -0.1298

Max Act: 0.0820. Min Act: -0.0001

Data Index: 263043 (C4 (Web Text))

Max Activating Token Index: 398