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

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

Neuron 4487 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3300. Min Range: -2.3300

Max Act: 2.3300. Min Act: -0.0000

Data Index: 957495 (C4 (Web Text))

Max Activating Token Index: 220

Text #1

Max Range: 2.3300. Min Range: -2.3300

Max Act: 2.2684. Min Act: -0.0000

Data Index: 1085885 (C4 (Web Text))

Max Activating Token Index: 996

Text #2

Max Range: 2.3300. Min Range: -2.3300

Max Act: 2.2287. Min Act: -0.0000

Data Index: 1208537 (C4 (Web Text))

Max Activating Token Index: 619

Text #3

Max Range: 2.3300. Min Range: -2.3300

Max Act: 2.1152. Min Act: -0.0000

Data Index: 850757 (C4 (Web Text))

Max Activating Token Index: 757

Text #4

Max Range: 2.3300. Min Range: -2.3300

Max Act: 2.0810. Min Act: -0.0000

Data Index: 533856 (C4 (Web Text))

Max Activating Token Index: 84

Text #5

Max Range: 2.3300. Min Range: -2.3300

Max Act: 2.2679. Min Act: -0.0000

Data Index: 754899 (C4 (Web Text))

Max Activating Token Index: 754

Text #6

Max Range: 2.3300. Min Range: -2.3300

Max Act: 2.1317. Min Act: -0.0000

Data Index: 68753 (C4 (Web Text))

Max Activating Token Index: 157

Text #7

Max Range: 2.3300. Min Range: -2.3300

Max Act: 1.9974. Min Act: -0.0000

Data Index: 221737 (C4 (Web Text))

Max Activating Token Index: 426

Text #8

Max Range: 2.3300. Min Range: -2.3300

Max Act: 2.0063. Min Act: -0.0000

Data Index: 230975 (C4 (Web Text))

Max Activating Token Index: 1021

Text #9

Max Range: 2.3300. Min Range: -2.3300

Max Act: 1.9840. Min Act: -0.0000

Data Index: 1357723 (C4 (Web Text))

Max Activating Token Index: 988

Text #10

Max Range: 2.3300. Min Range: -2.3300

Max Act: 1.7867. Min Act: -0.0000

Data Index: 485502 (C4 (Web Text))

Max Activating Token Index: 735

Text #11

Max Range: 2.3300. Min Range: -2.3300

Max Act: 1.9633. Min Act: -0.0000

Data Index: 72068 (C4 (Web Text))

Max Activating Token Index: 87

Text #12

Max Range: 2.3300. Min Range: -2.3300

Max Act: 1.9453. Min Act: -0.0000

Data Index: 878927 (C4 (Web Text))

Max Activating Token Index: 111

Text #13

Max Range: 2.3300. Min Range: -2.3300

Max Act: 1.9307. Min Act: -0.0000

Data Index: 1194209 (C4 (Web Text))

Max Activating Token Index: 14

Text #14

Max Range: 2.3300. Min Range: -2.3300

Max Act: 1.8127. Min Act: -0.0000

Data Index: 1350552 (C4 (Web Text))

Max Activating Token Index: 928

Text #15

Max Range: 2.3300. Min Range: -2.3300

Max Act: 1.8767. Min Act: -0.0000

Data Index: 205379 (C4 (Web Text))

Max Activating Token Index: 673

Text #16

Max Range: 2.3300. Min Range: -2.3300

Max Act: 1.8563. Min Act: -0.0000

Data Index: 918062 (C4 (Web Text))

Max Activating Token Index: 934

Text #17

Max Range: 2.3300. Min Range: -2.3300

Max Act: 1.8294. Min Act: -0.0000

Data Index: 1003940 (C4 (Web Text))

Max Activating Token Index: 531

Text #18

Max Range: 2.3300. Min Range: -2.3300

Max Act: 1.8143. Min Act: -0.0000

Data Index: 960422 (C4 (Web Text))

Max Activating Token Index: 76

Text #19

Max Range: 2.3300. Min Range: -2.3300

Max Act: 1.9005. Min Act: -0.0000

Data Index: 442091 (C4 (Web Text))

Max Activating Token Index: 420