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

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

Neuron 3116 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5053. Min Range: -0.5053

Max Act: 0.5053. Min Act: -0.0000

Data Index: 1505236 (Python Code)

Max Activating Token Index: 301

Text #1

Max Range: 0.5053. Min Range: -0.5053

Max Act: 0.3656. Min Act: -0.0000

Data Index: 1644556 (Python Code)

Max Activating Token Index: 63

Text #2

Max Range: 0.5053. Min Range: -0.5053

Max Act: 0.3723. Min Act: 0.0001

Data Index: 1146374 (C4 (Web Text))

Max Activating Token Index: 506

Text #3

Max Range: 0.5053. Min Range: -0.5053

Max Act: 0.3144. Min Act: -0.0000

Data Index: 311112 (C4 (Web Text))

Max Activating Token Index: 376

Text #4

Max Range: 0.5053. Min Range: -0.5053

Max Act: 0.3310. Min Act: -0.0000

Data Index: 209920 (C4 (Web Text))

Max Activating Token Index: 1006

Text #5

Max Range: 0.5053. Min Range: -0.5053

Max Act: 0.3023. Min Act: -0.0000

Data Index: 1382323 (Python Code)

Max Activating Token Index: 661

Text #6

Max Range: 0.5053. Min Range: -0.5053

Max Act: 0.3101. Min Act: -0.0000

Data Index: 78371 (C4 (Web Text))

Max Activating Token Index: 56

Text #7

Max Range: 0.5053. Min Range: -0.5053

Max Act: 0.3128. Min Act: -0.0000

Data Index: 1604188 (Python Code)

Max Activating Token Index: 212

Text #8

Max Range: 0.5053. Min Range: -0.5053

Max Act: 0.2821. Min Act: -0.0000

Data Index: 938404 (C4 (Web Text))

Max Activating Token Index: 783

Text #9

Max Range: 0.5053. Min Range: -0.5053

Max Act: 0.2631. Min Act: -0.0000

Data Index: 656066 (C4 (Web Text))

Max Activating Token Index: 900

Text #10

Max Range: 0.5053. Min Range: -0.5053

Max Act: 0.2886. Min Act: -0.0000

Data Index: 1286005 (C4 (Web Text))

Max Activating Token Index: 843

Text #11

Max Range: 0.5053. Min Range: -0.5053

Max Act: 0.2832. Min Act: -0.0000

Data Index: 650559 (C4 (Web Text))

Max Activating Token Index: 129

Text #12

Max Range: 0.5053. Min Range: -0.5053

Max Act: 0.2779. Min Act: -0.0000

Data Index: 1549312 (Python Code)

Max Activating Token Index: 995

Text #13

Max Range: 0.5053. Min Range: -0.5053

Max Act: 0.2661. Min Act: -0.0000

Data Index: 1480315 (Python Code)

Max Activating Token Index: 107

Text #14

Max Range: 0.5053. Min Range: -0.5053

Max Act: 0.2855. Min Act: -0.0000

Data Index: 1558402 (Python Code)

Max Activating Token Index: 309

Text #15

Max Range: 0.5053. Min Range: -0.5053

Max Act: 0.2718. Min Act: -0.0000

Data Index: 580502 (C4 (Web Text))

Max Activating Token Index: 143

Text #16

Max Range: 0.5053. Min Range: -0.5053

Max Act: 0.2728. Min Act: -0.0000

Data Index: 1256522 (C4 (Web Text))

Max Activating Token Index: 914

Text #17

Max Range: 0.5053. Min Range: -0.5053

Max Act: 0.2715. Min Act: -0.0000

Data Index: 1315631 (C4 (Web Text))

Max Activating Token Index: 305

Text #18

Max Range: 0.5053. Min Range: -0.5053

Max Act: 0.2698. Min Act: -0.0000

Data Index: 1013765 (C4 (Web Text))

Max Activating Token Index: 202

Text #19

Max Range: 0.5053. Min Range: -0.5053

Max Act: 0.2704. Min Act: -0.0000

Data Index: 1561396 (Python Code)

Max Activating Token Index: 379