Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3716 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3264. Min Range: -1.3264

Max Act: 1.3264. Min Act: -0.0001

Data Index: 1019126 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 1.3264. Min Range: -1.3264

Max Act: 1.0992. Min Act: -0.0001

Data Index: 41383 (C4 (Web Text))

Max Activating Token Index: 710

Text #2

Max Range: 1.3264. Min Range: -1.3264

Max Act: 0.9980. Min Act: -0.0001

Data Index: 389588 (C4 (Web Text))

Max Activating Token Index: 520

Text #3

Max Range: 1.3264. Min Range: -1.3264

Max Act: 0.9513. Min Act: -0.0001

Data Index: 130125 (C4 (Web Text))

Max Activating Token Index: 735

Text #4

Max Range: 1.3264. Min Range: -1.3264

Max Act: 0.7740. Min Act: -0.0001

Data Index: 19417 (C4 (Web Text))

Max Activating Token Index: 959

Text #5

Max Range: 1.3264. Min Range: -1.3264

Max Act: 1.0665. Min Act: -0.0001

Data Index: 1110965 (C4 (Web Text))

Max Activating Token Index: 726

Text #6

Max Range: 1.3264. Min Range: -1.3264

Max Act: 0.9495. Min Act: -0.0001

Data Index: 355033 (C4 (Web Text))

Max Activating Token Index: 384

Text #7

Max Range: 1.3264. Min Range: -1.3264

Max Act: 0.9998. Min Act: -0.0001

Data Index: 1060450 (C4 (Web Text))

Max Activating Token Index: 362

Text #8

Max Range: 1.3264. Min Range: -1.3264

Max Act: 0.9581. Min Act: -0.0001

Data Index: 788480 (C4 (Web Text))

Max Activating Token Index: 608

Text #9

Max Range: 1.3264. Min Range: -1.3264

Max Act: 0.8719. Min Act: -0.0001

Data Index: 793608 (C4 (Web Text))

Max Activating Token Index: 885

Text #10

Max Range: 1.3264. Min Range: -1.3264

Max Act: 0.9782. Min Act: -0.0001

Data Index: 309582 (C4 (Web Text))

Max Activating Token Index: 501

Text #11

Max Range: 1.3264. Min Range: -1.3264

Max Act: 0.9365. Min Act: -0.0001

Data Index: 1217648 (C4 (Web Text))

Max Activating Token Index: 919

Text #12

Max Range: 1.3264. Min Range: -1.3264

Max Act: 0.9537. Min Act: -0.0001

Data Index: 975948 (C4 (Web Text))

Max Activating Token Index: 1014

Text #13

Max Range: 1.3264. Min Range: -1.3264

Max Act: 0.9516. Min Act: -0.0001

Data Index: 1358455 (C4 (Web Text))

Max Activating Token Index: 637

Text #14

Max Range: 1.3264. Min Range: -1.3264

Max Act: 0.9427. Min Act: -0.0001

Data Index: 589714 (C4 (Web Text))

Max Activating Token Index: 537

Text #15

Max Range: 1.3264. Min Range: -1.3264

Max Act: 0.8829. Min Act: -0.0001

Data Index: 780934 (C4 (Web Text))

Max Activating Token Index: 968

Text #16

Max Range: 1.3264. Min Range: -1.3264

Max Act: 0.7946. Min Act: -0.0001

Data Index: 420657 (C4 (Web Text))

Max Activating Token Index: 99

Text #17

Max Range: 1.3264. Min Range: -1.3264

Max Act: 0.9488. Min Act: -0.0001

Data Index: 110296 (C4 (Web Text))

Max Activating Token Index: 519

Text #18

Max Range: 1.3264. Min Range: -1.3264

Max Act: 0.9791. Min Act: -0.0001

Data Index: 1041899 (C4 (Web Text))

Max Activating Token Index: 936

Text #19

Max Range: 1.3264. Min Range: -1.3264

Max Act: 0.8294. Min Act: -0.0001

Data Index: 912845 (C4 (Web Text))

Max Activating Token Index: 565