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

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

Neuron 2903 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1444. Min Act: -0.0001

Data Index: 7365 (C4 (Web Text))

Max Activating Token Index: 885

Text #1

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1362. Min Act: -0.0001

Data Index: 1269468 (C4 (Web Text))

Max Activating Token Index: 359

Text #2

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1266. Min Act: -0.0001

Data Index: 762314 (C4 (Web Text))

Max Activating Token Index: 816

Text #3

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1095. Min Act: -0.0001

Data Index: 910345 (C4 (Web Text))

Max Activating Token Index: 101

Text #4

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.1047. Min Act: -0.0001

Data Index: 709876 (C4 (Web Text))

Max Activating Token Index: 31

Text #5

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0929. Min Act: -0.0001

Data Index: 969667 (C4 (Web Text))

Max Activating Token Index: 314

Text #6

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0821. Min Act: -0.0001

Data Index: 1203095 (C4 (Web Text))

Max Activating Token Index: 362

Text #7

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0884. Min Act: -0.0001

Data Index: 1300016 (C4 (Web Text))

Max Activating Token Index: 977

Text #8

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0857. Min Act: -0.0001

Data Index: 365840 (C4 (Web Text))

Max Activating Token Index: 323

Text #9

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0890. Min Act: -0.0001

Data Index: 17724 (C4 (Web Text))

Max Activating Token Index: 6

Text #10

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0796. Min Act: -0.0001

Data Index: 701551 (C4 (Web Text))

Max Activating Token Index: 786

Text #11

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0835. Min Act: -0.0001

Data Index: 395786 (C4 (Web Text))

Max Activating Token Index: 131

Text #12

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0726. Min Act: -0.0001

Data Index: 1208439 (C4 (Web Text))

Max Activating Token Index: 752

Text #13

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0836. Min Act: -0.0001

Data Index: 1276226 (C4 (Web Text))

Max Activating Token Index: 314

Text #14

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0904. Min Act: -0.0001

Data Index: 268544 (C4 (Web Text))

Max Activating Token Index: 677

Text #15

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0752. Min Act: -0.0001

Data Index: 875672 (C4 (Web Text))

Max Activating Token Index: 152

Text #16

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0747. Min Act: -0.0001

Data Index: 85434 (C4 (Web Text))

Max Activating Token Index: 201

Text #17

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0753. Min Act: -0.0001

Data Index: 296048 (C4 (Web Text))

Max Activating Token Index: 214

Text #18

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0845. Min Act: -0.0001

Data Index: 488513 (C4 (Web Text))

Max Activating Token Index: 790

Text #19

Max Range: 0.1444. Min Range: -0.1444

Max Act: 0.0763. Min Act: -0.0001

Data Index: 18936 (C4 (Web Text))

Max Activating Token Index: 89