Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 334 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.7499. Min Act: -0.0003

Data Index: 494837 (C4 (Web Text))

Max Activating Token Index: 564

Text #1

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.7354. Min Act: -0.0003

Data Index: 1274572 (C4 (Web Text))

Max Activating Token Index: 18

Text #2

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.7089. Min Act: -0.0003

Data Index: 775188 (C4 (Web Text))

Max Activating Token Index: 824

Text #3

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.6330. Min Act: -0.0003

Data Index: 321054 (C4 (Web Text))

Max Activating Token Index: 83

Text #4

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.6632. Min Act: -0.0003

Data Index: 682612 (C4 (Web Text))

Max Activating Token Index: 19

Text #5

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.6650. Min Act: -0.0003

Data Index: 402988 (C4 (Web Text))

Max Activating Token Index: 738

Text #6

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.6167. Min Act: -0.0003

Data Index: 220911 (C4 (Web Text))

Max Activating Token Index: 127

Text #7

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.5757. Min Act: -0.0003

Data Index: 637276 (C4 (Web Text))

Max Activating Token Index: 11

Text #8

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.6320. Min Act: -0.0003

Data Index: 702735 (C4 (Web Text))

Max Activating Token Index: 35

Text #9

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.6795. Min Act: -0.0003

Data Index: 1084927 (C4 (Web Text))

Max Activating Token Index: 122

Text #10

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.6315. Min Act: -0.0003

Data Index: 245126 (C4 (Web Text))

Max Activating Token Index: 108

Text #11

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.6395. Min Act: -0.0003

Data Index: 914135 (C4 (Web Text))

Max Activating Token Index: 99

Text #12

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.6185. Min Act: -0.0003

Data Index: 1194510 (C4 (Web Text))

Max Activating Token Index: 776

Text #13

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.5839. Min Act: -0.0003

Data Index: 1315549 (C4 (Web Text))

Max Activating Token Index: 331

Text #14

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.5972. Min Act: -0.0003

Data Index: 131313 (C4 (Web Text))

Max Activating Token Index: 190

Text #15

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.6363. Min Act: -0.0003

Data Index: 1139826 (C4 (Web Text))

Max Activating Token Index: 366

Text #16

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.5955. Min Act: -0.0003

Data Index: 795746 (C4 (Web Text))

Max Activating Token Index: 78

Text #17

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.5892. Min Act: -0.0003

Data Index: 1156311 (C4 (Web Text))

Max Activating Token Index: 551

Text #18

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.6287. Min Act: -0.0003

Data Index: 199137 (C4 (Web Text))

Max Activating Token Index: 360

Text #19

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.6528. Min Act: -0.0003

Data Index: 779005 (C4 (Web Text))

Max Activating Token Index: 67