Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2451 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9767. Min Range: -0.9767

Max Act: 0.9767. Min Act: -0.0000

Data Index: 462966 (C4 (Web Text))

Max Activating Token Index: 978

Text #1

Max Range: 0.9767. Min Range: -0.9767

Max Act: 0.9103. Min Act: -0.0000

Data Index: 424130 (C4 (Web Text))

Max Activating Token Index: 69

Text #2

Max Range: 0.9767. Min Range: -0.9767

Max Act: 0.8924. Min Act: -0.0000

Data Index: 355964 (C4 (Web Text))

Max Activating Token Index: 505

Text #3

Max Range: 0.9767. Min Range: -0.9767

Max Act: 0.9029. Min Act: -0.0000

Data Index: 226071 (C4 (Web Text))

Max Activating Token Index: 42

Text #4

Max Range: 0.9767. Min Range: -0.9767

Max Act: 0.8952. Min Act: -0.0000

Data Index: 588151 (C4 (Web Text))

Max Activating Token Index: 805

Text #5

Max Range: 0.9767. Min Range: -0.9767

Max Act: 0.8386. Min Act: -0.0000

Data Index: 107294 (C4 (Web Text))

Max Activating Token Index: 70

Text #6

Max Range: 0.9767. Min Range: -0.9767

Max Act: 0.8163. Min Act: -0.0000

Data Index: 579349 (C4 (Web Text))

Max Activating Token Index: 331

Text #7

Max Range: 0.9767. Min Range: -0.9767

Max Act: 0.7847. Min Act: -0.0000

Data Index: 715506 (C4 (Web Text))

Max Activating Token Index: 112

Text #8

Max Range: 0.9767. Min Range: -0.9767

Max Act: 0.7733. Min Act: -0.0000

Data Index: 701313 (C4 (Web Text))

Max Activating Token Index: 56

Text #9

Max Range: 0.9767. Min Range: -0.9767

Max Act: 0.7545. Min Act: -0.0000

Data Index: 504382 (C4 (Web Text))

Max Activating Token Index: 787

Text #10

Max Range: 0.9767. Min Range: -0.9767

Max Act: 0.7969. Min Act: -0.0000

Data Index: 1176572 (C4 (Web Text))

Max Activating Token Index: 145

Text #11

Max Range: 0.9767. Min Range: -0.9767

Max Act: 0.8068. Min Act: -0.0000

Data Index: 101689 (C4 (Web Text))

Max Activating Token Index: 841

Text #12

Max Range: 0.9767. Min Range: -0.9767

Max Act: 0.7499. Min Act: -0.0000

Data Index: 970063 (C4 (Web Text))

Max Activating Token Index: 85

Text #13

Max Range: 0.9767. Min Range: -0.9767

Max Act: 0.7515. Min Act: -0.0000

Data Index: 628390 (C4 (Web Text))

Max Activating Token Index: 908

Text #14

Max Range: 0.9767. Min Range: -0.9767

Max Act: 0.7449. Min Act: -0.0000

Data Index: 1227164 (C4 (Web Text))

Max Activating Token Index: 276

Text #15

Max Range: 0.9767. Min Range: -0.9767

Max Act: 0.7390. Min Act: -0.0000

Data Index: 1232301 (C4 (Web Text))

Max Activating Token Index: 136

Text #16

Max Range: 0.9767. Min Range: -0.9767

Max Act: 0.6879. Min Act: -0.0000

Data Index: 745972 (C4 (Web Text))

Max Activating Token Index: 684

Text #17

Max Range: 0.9767. Min Range: -0.9767

Max Act: 0.6792. Min Act: -0.0000

Data Index: 899985 (C4 (Web Text))

Max Activating Token Index: 458

Text #18

Max Range: 0.9767. Min Range: -0.9767

Max Act: 0.6787. Min Act: -0.0000

Data Index: 1313375 (C4 (Web Text))

Max Activating Token Index: 636

Text #19

Max Range: 0.9767. Min Range: -0.9767

Max Act: 0.7320. Min Act: -0.0000

Data Index: 1263522 (C4 (Web Text))

Max Activating Token Index: 618