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

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

Neuron 3379 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.1146. Min Act: -0.0000

Data Index: 1538824 (Python Code)

Max Activating Token Index: 176

Text #1

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.1052. Min Act: -0.0000

Data Index: 1445689 (Python Code)

Max Activating Token Index: 868

Text #2

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.1002. Min Act: -0.0000

Data Index: 1555846 (Python Code)

Max Activating Token Index: 803

Text #3

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.1008. Min Act: -0.0000

Data Index: 1455978 (Python Code)

Max Activating Token Index: 247

Text #4

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0925. Min Act: -0.0000

Data Index: 1460612 (Python Code)

Max Activating Token Index: 237

Text #5

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0954. Min Act: -0.0000

Data Index: 1396702 (Python Code)

Max Activating Token Index: 344

Text #6

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0863. Min Act: -0.0000

Data Index: 769159 (C4 (Web Text))

Max Activating Token Index: 111

Text #7

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0895. Min Act: -0.0000

Data Index: 1391589 (Python Code)

Max Activating Token Index: 915

Text #8

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.1008. Min Act: -0.0000

Data Index: 1628892 (Python Code)

Max Activating Token Index: 958

Text #9

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0855. Min Act: -0.0000

Data Index: 1499182 (Python Code)

Max Activating Token Index: 564

Text #10

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0900. Min Act: -0.0000

Data Index: 1463256 (Python Code)

Max Activating Token Index: 931

Text #11

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0801. Min Act: -0.0000

Data Index: 364045 (C4 (Web Text))

Max Activating Token Index: 971

Text #12

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0759. Min Act: -0.0000

Data Index: 1612374 (Python Code)

Max Activating Token Index: 739

Text #13

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0821. Min Act: -0.0000

Data Index: 1503078 (Python Code)

Max Activating Token Index: 63

Text #14

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0796. Min Act: -0.0000

Data Index: 1627166 (Python Code)

Max Activating Token Index: 303

Text #15

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0831. Min Act: -0.0000

Data Index: 1330821 (C4 (Web Text))

Max Activating Token Index: 109

Text #16

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0793. Min Act: -0.0000

Data Index: 1529871 (Python Code)

Max Activating Token Index: 262

Text #17

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0816. Min Act: -0.0000

Data Index: 1524679 (Python Code)

Max Activating Token Index: 631

Text #18

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0813. Min Act: -0.0000

Data Index: 694853 (C4 (Web Text))

Max Activating Token Index: 34

Text #19

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0827. Min Act: -0.0000

Data Index: 1421920 (Python Code)

Max Activating Token Index: 200