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

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

Neuron 3519 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0349. Min Range: -2.0349

Max Act: 2.0349. Min Act: -0.0000

Data Index: 1294849 (C4 (Web Text))

Max Activating Token Index: 801

Text #1

Max Range: 2.0349. Min Range: -2.0349

Max Act: 1.9281. Min Act: -0.0000

Data Index: 592771 (C4 (Web Text))

Max Activating Token Index: 692

Text #2

Max Range: 2.0349. Min Range: -2.0349

Max Act: 1.6854. Min Act: -0.0000

Data Index: 353335 (C4 (Web Text))

Max Activating Token Index: 813

Text #3

Max Range: 2.0349. Min Range: -2.0349

Max Act: 1.5321. Min Act: -0.0000

Data Index: 532531 (C4 (Web Text))

Max Activating Token Index: 886

Text #4

Max Range: 2.0349. Min Range: -2.0349

Max Act: 1.5949. Min Act: -0.0000

Data Index: 906814 (C4 (Web Text))

Max Activating Token Index: 664

Text #5

Max Range: 2.0349. Min Range: -2.0349

Max Act: 1.5083. Min Act: -0.0000

Data Index: 28581 (C4 (Web Text))

Max Activating Token Index: 890

Text #6

Max Range: 2.0349. Min Range: -2.0349

Max Act: 1.5340. Min Act: -0.0000

Data Index: 742674 (C4 (Web Text))

Max Activating Token Index: 647

Text #7

Max Range: 2.0349. Min Range: -2.0349

Max Act: 1.4066. Min Act: -0.0000

Data Index: 637632 (C4 (Web Text))

Max Activating Token Index: 728

Text #8

Max Range: 2.0349. Min Range: -2.0349

Max Act: 1.4050. Min Act: -0.0000

Data Index: 847928 (C4 (Web Text))

Max Activating Token Index: 316

Text #9

Max Range: 2.0349. Min Range: -2.0349

Max Act: 1.4566. Min Act: -0.0000

Data Index: 1147333 (C4 (Web Text))

Max Activating Token Index: 109

Text #10

Max Range: 2.0349. Min Range: -2.0349

Max Act: 1.4442. Min Act: -0.0000

Data Index: 476610 (C4 (Web Text))

Max Activating Token Index: 329

Text #11

Max Range: 2.0349. Min Range: -2.0349

Max Act: 1.3449. Min Act: -0.0000

Data Index: 344647 (C4 (Web Text))

Max Activating Token Index: 16

Text #12

Max Range: 2.0349. Min Range: -2.0349

Max Act: 1.3281. Min Act: -0.0000

Data Index: 169090 (C4 (Web Text))

Max Activating Token Index: 1012

Text #13

Max Range: 2.0349. Min Range: -2.0349

Max Act: 1.4059. Min Act: -0.0000

Data Index: 1180767 (C4 (Web Text))

Max Activating Token Index: 228

Text #14

Max Range: 2.0349. Min Range: -2.0349

Max Act: 1.3981. Min Act: -0.0000

Data Index: 264029 (C4 (Web Text))

Max Activating Token Index: 793

Text #15

Max Range: 2.0349. Min Range: -2.0349

Max Act: 1.4533. Min Act: -0.0000

Data Index: 743081 (C4 (Web Text))

Max Activating Token Index: 760

Text #16

Max Range: 2.0349. Min Range: -2.0349

Max Act: 1.3553. Min Act: -0.0000

Data Index: 1279981 (C4 (Web Text))

Max Activating Token Index: 361

Text #17

Max Range: 2.0349. Min Range: -2.0349

Max Act: 1.2416. Min Act: -0.0000

Data Index: 742132 (C4 (Web Text))

Max Activating Token Index: 34

Text #18

Max Range: 2.0349. Min Range: -2.0349

Max Act: 1.2976. Min Act: -0.0000

Data Index: 1143796 (C4 (Web Text))

Max Activating Token Index: 602

Text #19

Max Range: 2.0349. Min Range: -2.0349

Max Act: 1.3429. Min Act: -0.0000

Data Index: 1353665 (C4 (Web Text))

Max Activating Token Index: 134