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

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

Neuron 1996 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: 1.6884. Min Range: -1.6884

Max Act: 1.6884. Min Act: -0.0000

Data Index: 9891 (C4 (Web Text))

Max Activating Token Index: 1017

Text #1

Max Range: 1.6884. Min Range: -1.6884

Max Act: 1.5747. Min Act: -0.0000

Data Index: 813511 (C4 (Web Text))

Max Activating Token Index: 356

Text #2

Max Range: 1.6884. Min Range: -1.6884

Max Act: 1.3383. Min Act: -0.0000

Data Index: 532197 (C4 (Web Text))

Max Activating Token Index: 797

Text #3

Max Range: 1.6884. Min Range: -1.6884

Max Act: 1.3473. Min Act: -0.0000

Data Index: 1129467 (C4 (Web Text))

Max Activating Token Index: 447

Text #4

Max Range: 1.6884. Min Range: -1.6884

Max Act: 1.2767. Min Act: -0.0000

Data Index: 492227 (C4 (Web Text))

Max Activating Token Index: 371

Text #5

Max Range: 1.6884. Min Range: -1.6884

Max Act: 1.2229. Min Act: -0.0000

Data Index: 366712 (C4 (Web Text))

Max Activating Token Index: 361

Text #6

Max Range: 1.6884. Min Range: -1.6884

Max Act: 1.2813. Min Act: -0.0000

Data Index: 416806 (C4 (Web Text))

Max Activating Token Index: 997

Text #7

Max Range: 1.6884. Min Range: -1.6884

Max Act: 1.2528. Min Act: -0.0000

Data Index: 220910 (C4 (Web Text))

Max Activating Token Index: 570

Text #8

Max Range: 1.6884. Min Range: -1.6884

Max Act: 1.1349. Min Act: -0.0000

Data Index: 753266 (C4 (Web Text))

Max Activating Token Index: 993

Text #9

Max Range: 1.6884. Min Range: -1.6884

Max Act: 1.1655. Min Act: -0.0000

Data Index: 1005387 (C4 (Web Text))

Max Activating Token Index: 894

Text #10

Max Range: 1.6884. Min Range: -1.6884

Max Act: 1.1986. Min Act: -0.0000

Data Index: 133453 (C4 (Web Text))

Max Activating Token Index: 58

Text #11

Max Range: 1.6884. Min Range: -1.6884

Max Act: 1.2489. Min Act: -0.0000

Data Index: 1233200 (C4 (Web Text))

Max Activating Token Index: 631

Text #12

Max Range: 1.6884. Min Range: -1.6884

Max Act: 1.1643. Min Act: -0.0000

Data Index: 1345376 (C4 (Web Text))

Max Activating Token Index: 1015

Text #13

Max Range: 1.6884. Min Range: -1.6884

Max Act: 1.1609. Min Act: -0.0000

Data Index: 162127 (C4 (Web Text))

Max Activating Token Index: 349

Text #14

Max Range: 1.6884. Min Range: -1.6884

Max Act: 1.1498. Min Act: -0.0000

Data Index: 1077654 (C4 (Web Text))

Max Activating Token Index: 376

Text #15

Max Range: 1.6884. Min Range: -1.6884

Max Act: 1.0300. Min Act: -0.0000

Data Index: 828848 (C4 (Web Text))

Max Activating Token Index: 863

Text #16

Max Range: 1.6884. Min Range: -1.6884

Max Act: 1.0917. Min Act: -0.0000

Data Index: 491680 (C4 (Web Text))

Max Activating Token Index: 1020

Text #17

Max Range: 1.6884. Min Range: -1.6884

Max Act: 1.0916. Min Act: -0.0000

Data Index: 592759 (C4 (Web Text))

Max Activating Token Index: 594

Text #18

Max Range: 1.6884. Min Range: -1.6884

Max Act: 1.1737. Min Act: -0.0000

Data Index: 584417 (C4 (Web Text))

Max Activating Token Index: 694

Text #19

Max Range: 1.6884. Min Range: -1.6884

Max Act: 1.1298. Min Act: -0.0000

Data Index: 776016 (C4 (Web Text))

Max Activating Token Index: 479