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

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

Neuron 1260 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1681. Min Range: -1.1681

Max Act: 1.1580. Min Act: -0.0001

Data Index: 49446 (C4 (Web Text))

Max Activating Token Index: 138

Text #1

Max Range: 1.1681. Min Range: -1.1681

Max Act: 1.1681. Min Act: -0.0001

Data Index: 472862 (C4 (Web Text))

Max Activating Token Index: 510

Text #2

Max Range: 1.1681. Min Range: -1.1681

Max Act: 0.9219. Min Act: -0.0001

Data Index: 1168724 (C4 (Web Text))

Max Activating Token Index: 837

Text #3

Max Range: 1.1681. Min Range: -1.1681

Max Act: 0.9604. Min Act: -0.0001

Data Index: 289324 (C4 (Web Text))

Max Activating Token Index: 686

Text #4

Max Range: 1.1681. Min Range: -1.1681

Max Act: 0.9244. Min Act: -0.0001

Data Index: 572170 (C4 (Web Text))

Max Activating Token Index: 645

Text #5

Max Range: 1.1681. Min Range: -1.1681

Max Act: 0.9121. Min Act: -0.0001

Data Index: 625412 (C4 (Web Text))

Max Activating Token Index: 68

Text #6

Max Range: 1.1681. Min Range: -1.1681

Max Act: 0.8888. Min Act: -0.0001

Data Index: 1444497 (Python Code)

Max Activating Token Index: 576

Text #7

Max Range: 1.1681. Min Range: -1.1681

Max Act: 0.8040. Min Act: -0.0001

Data Index: 1162218 (C4 (Web Text))

Max Activating Token Index: 961

Text #8

Max Range: 1.1681. Min Range: -1.1681

Max Act: 0.8738. Min Act: -0.0001

Data Index: 823309 (C4 (Web Text))

Max Activating Token Index: 523

Text #9

Max Range: 1.1681. Min Range: -1.1681

Max Act: 0.8793. Min Act: -0.0001

Data Index: 1464396 (Python Code)

Max Activating Token Index: 917

Text #10

Max Range: 1.1681. Min Range: -1.1681

Max Act: 0.8512. Min Act: -0.0001

Data Index: 200810 (C4 (Web Text))

Max Activating Token Index: 867

Text #11

Max Range: 1.1681. Min Range: -1.1681

Max Act: 0.8866. Min Act: -0.0001

Data Index: 762054 (C4 (Web Text))

Max Activating Token Index: 517

Text #12

Max Range: 1.1681. Min Range: -1.1681

Max Act: 0.8064. Min Act: -0.0001

Data Index: 1263036 (C4 (Web Text))

Max Activating Token Index: 183

Text #13

Max Range: 1.1681. Min Range: -1.1681

Max Act: 0.8323. Min Act: -0.0001

Data Index: 867523 (C4 (Web Text))

Max Activating Token Index: 422

Text #14

Max Range: 1.1681. Min Range: -1.1681

Max Act: 0.8219. Min Act: -0.0001

Data Index: 1175525 (C4 (Web Text))

Max Activating Token Index: 14

Text #15

Max Range: 1.1681. Min Range: -1.1681

Max Act: 0.8203. Min Act: -0.0001

Data Index: 1648504 (Python Code)

Max Activating Token Index: 91

Text #16

Max Range: 1.1681. Min Range: -1.1681

Max Act: 0.7952. Min Act: -0.0001

Data Index: 1237957 (C4 (Web Text))

Max Activating Token Index: 407

Text #17

Max Range: 1.1681. Min Range: -1.1681

Max Act: 0.8347. Min Act: -0.0001

Data Index: 938071 (C4 (Web Text))

Max Activating Token Index: 175

Text #18

Max Range: 1.1681. Min Range: -1.1681

Max Act: 0.8167. Min Act: -0.0001

Data Index: 355093 (C4 (Web Text))

Max Activating Token Index: 128

Text #19

Max Range: 1.1681. Min Range: -1.1681

Max Act: 0.7489. Min Act: -0.0001

Data Index: 773563 (C4 (Web Text))

Max Activating Token Index: 164