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

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

Neuron 5970 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.1105. Min Act: -0.0002

Data Index: 353561 (C4 (Web Text))

Max Activating Token Index: 470

Text #1

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.1049. Min Act: -0.0002

Data Index: 1258180 (C4 (Web Text))

Max Activating Token Index: 298

Text #2

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0987. Min Act: -0.0002

Data Index: 614630 (C4 (Web Text))

Max Activating Token Index: 236

Text #3

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0947. Min Act: -0.0002

Data Index: 1156020 (C4 (Web Text))

Max Activating Token Index: 771

Text #4

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0914. Min Act: -0.0002

Data Index: 1225233 (C4 (Web Text))

Max Activating Token Index: 594

Text #5

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0863. Min Act: -0.0002

Data Index: 1270447 (C4 (Web Text))

Max Activating Token Index: 601

Text #6

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0850. Min Act: -0.0002

Data Index: 39770 (C4 (Web Text))

Max Activating Token Index: 297

Text #7

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0846. Min Act: -0.0002

Data Index: 1596418 (Python Code)

Max Activating Token Index: 810

Text #8

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0806. Min Act: -0.0002

Data Index: 160018 (C4 (Web Text))

Max Activating Token Index: 298

Text #9

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0811. Min Act: -0.0002

Data Index: 1369440 (Python Code)

Max Activating Token Index: 676

Text #10

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0819. Min Act: -0.0002

Data Index: 1479664 (Python Code)

Max Activating Token Index: 877

Text #11

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0802. Min Act: -0.0002

Data Index: 1522331 (Python Code)

Max Activating Token Index: 721

Text #12

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0798. Min Act: -0.0002

Data Index: 1463691 (Python Code)

Max Activating Token Index: 651

Text #13

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0769. Min Act: -0.0002

Data Index: 1628658 (Python Code)

Max Activating Token Index: 637

Text #14

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0768. Min Act: -0.0002

Data Index: 1555262 (Python Code)

Max Activating Token Index: 579

Text #15

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0825. Min Act: -0.0002

Data Index: 1436541 (Python Code)

Max Activating Token Index: 676

Text #16

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0780. Min Act: -0.0002

Data Index: 1652466 (Python Code)

Max Activating Token Index: 721

Text #17

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0731. Min Act: -0.0002

Data Index: 1368282 (Python Code)

Max Activating Token Index: 702

Text #18

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0787. Min Act: -0.0002

Data Index: 1361078 (Python Code)

Max Activating Token Index: 533

Text #19

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0783. Min Act: -0.0002

Data Index: 1526779 (Python Code)

Max Activating Token Index: 856