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

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

Neuron 2965 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: 1.1433. Min Range: -1.1433

Max Act: 1.1433. Min Act: -0.0000

Data Index: 911461 (C4 (Web Text))

Max Activating Token Index: 474

Text #1

Max Range: 1.1433. Min Range: -1.1433

Max Act: 1.1086. Min Act: -0.0000

Data Index: 153024 (C4 (Web Text))

Max Activating Token Index: 318

Text #2

Max Range: 1.1433. Min Range: -1.1433

Max Act: 1.0353. Min Act: -0.0001

Data Index: 812861 (C4 (Web Text))

Max Activating Token Index: 434

Text #3

Max Range: 1.1433. Min Range: -1.1433

Max Act: 1.0063. Min Act: -0.0000

Data Index: 902720 (C4 (Web Text))

Max Activating Token Index: 416

Text #4

Max Range: 1.1433. Min Range: -1.1433

Max Act: 1.0173. Min Act: -0.0000

Data Index: 530529 (C4 (Web Text))

Max Activating Token Index: 32

Text #5

Max Range: 1.1433. Min Range: -1.1433

Max Act: 1.0590. Min Act: -0.0000

Data Index: 334632 (C4 (Web Text))

Max Activating Token Index: 217

Text #6

Max Range: 1.1433. Min Range: -1.1433

Max Act: 0.9326. Min Act: -0.0000

Data Index: 371851 (C4 (Web Text))

Max Activating Token Index: 698

Text #7

Max Range: 1.1433. Min Range: -1.1433

Max Act: 0.9963. Min Act: -0.0000

Data Index: 324216 (C4 (Web Text))

Max Activating Token Index: 16

Text #8

Max Range: 1.1433. Min Range: -1.1433

Max Act: 1.0338. Min Act: -0.0001

Data Index: 855460 (C4 (Web Text))

Max Activating Token Index: 714

Text #9

Max Range: 1.1433. Min Range: -1.1433

Max Act: 0.8452. Min Act: -0.0001

Data Index: 583952 (C4 (Web Text))

Max Activating Token Index: 411

Text #10

Max Range: 1.1433. Min Range: -1.1433

Max Act: 0.9316. Min Act: -0.0000

Data Index: 114016 (C4 (Web Text))

Max Activating Token Index: 462

Text #11

Max Range: 1.1433. Min Range: -1.1433

Max Act: 0.9806. Min Act: -0.0000

Data Index: 674975 (C4 (Web Text))

Max Activating Token Index: 993

Text #12

Max Range: 1.1433. Min Range: -1.1433

Max Act: 0.8879. Min Act: -0.0000

Data Index: 922791 (C4 (Web Text))

Max Activating Token Index: 577

Text #13

Max Range: 1.1433. Min Range: -1.1433

Max Act: 0.9791. Min Act: -0.0000

Data Index: 99576 (C4 (Web Text))

Max Activating Token Index: 808

Text #14

Max Range: 1.1433. Min Range: -1.1433

Max Act: 0.8465. Min Act: -0.0000

Data Index: 488533 (C4 (Web Text))

Max Activating Token Index: 524

Text #15

Max Range: 1.1433. Min Range: -1.1433

Max Act: 0.7811. Min Act: -0.0000

Data Index: 1074370 (C4 (Web Text))

Max Activating Token Index: 972

Text #16

Max Range: 1.1433. Min Range: -1.1433

Max Act: 0.7945. Min Act: -0.0000

Data Index: 1277982 (C4 (Web Text))

Max Activating Token Index: 37

Text #17

Max Range: 1.1433. Min Range: -1.1433

Max Act: 0.7328. Min Act: -0.0000

Data Index: 648854 (C4 (Web Text))

Max Activating Token Index: 40

Text #18

Max Range: 1.1433. Min Range: -1.1433

Max Act: 0.8059. Min Act: -0.0000

Data Index: 949739 (C4 (Web Text))

Max Activating Token Index: 210

Text #19

Max Range: 1.1433. Min Range: -1.1433

Max Act: 0.7828. Min Act: -0.0000

Data Index: 322481 (C4 (Web Text))

Max Activating Token Index: 20