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

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

Neuron 2565 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.1076. Min Act: -0.0000

Data Index: 871456 (C4 (Web Text))

Max Activating Token Index: 261

Text #1

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0853. Min Act: -0.0000

Data Index: 766718 (C4 (Web Text))

Max Activating Token Index: 44

Text #2

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0836. Min Act: -0.0001

Data Index: 1646708 (Python Code)

Max Activating Token Index: 897

Text #3

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0819. Min Act: -0.0000

Data Index: 228437 (C4 (Web Text))

Max Activating Token Index: 138

Text #4

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0765. Min Act: -0.0001

Data Index: 1453821 (Python Code)

Max Activating Token Index: 662

Text #5

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0838. Min Act: -0.0000

Data Index: 1193463 (C4 (Web Text))

Max Activating Token Index: 267

Text #6

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0843. Min Act: -0.0000

Data Index: 1413167 (Python Code)

Max Activating Token Index: 222

Text #7

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0821. Min Act: -0.0000

Data Index: 1025732 (C4 (Web Text))

Max Activating Token Index: 602

Text #8

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0769. Min Act: -0.0000

Data Index: 888847 (C4 (Web Text))

Max Activating Token Index: 894

Text #9

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0737. Min Act: -0.0001

Data Index: 606222 (C4 (Web Text))

Max Activating Token Index: 282

Text #10

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0776. Min Act: -0.0000

Data Index: 716634 (C4 (Web Text))

Max Activating Token Index: 29

Text #11

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0709. Min Act: -0.0000

Data Index: 1176260 (C4 (Web Text))

Max Activating Token Index: 639

Text #12

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0742. Min Act: -0.0000

Data Index: 360990 (C4 (Web Text))

Max Activating Token Index: 279

Text #13

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0728. Min Act: -0.0001

Data Index: 1565799 (Python Code)

Max Activating Token Index: 141

Text #14

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0727. Min Act: -0.0001

Data Index: 1499149 (Python Code)

Max Activating Token Index: 1009

Text #15

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0681. Min Act: -0.0000

Data Index: 47095 (C4 (Web Text))

Max Activating Token Index: 860

Text #16

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0760. Min Act: -0.0000

Data Index: 1312448 (C4 (Web Text))

Max Activating Token Index: 688

Text #17

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0749. Min Act: -0.0001

Data Index: 527544 (C4 (Web Text))

Max Activating Token Index: 11

Text #18

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0692. Min Act: -0.0000

Data Index: 1228881 (C4 (Web Text))

Max Activating Token Index: 126

Text #19

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0719. Min Act: -0.0000

Data Index: 691019 (C4 (Web Text))

Max Activating Token Index: 38