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

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

Neuron 1064 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.6691. Min Act: -0.0000

Data Index: 328467 (C4 (Web Text))

Max Activating Token Index: 742

Text #1

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.6586. Min Act: -0.0000

Data Index: 1225374 (C4 (Web Text))

Max Activating Token Index: 933

Text #2

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.5673. Min Act: -0.0000

Data Index: 816699 (C4 (Web Text))

Max Activating Token Index: 629

Text #3

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.6105. Min Act: -0.0000

Data Index: 978654 (C4 (Web Text))

Max Activating Token Index: 503

Text #4

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.4809. Min Act: -0.0000

Data Index: 371714 (C4 (Web Text))

Max Activating Token Index: 537

Text #5

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.3878. Min Act: -0.0000

Data Index: 867797 (C4 (Web Text))

Max Activating Token Index: 371

Text #6

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.4126. Min Act: -0.0000

Data Index: 175117 (C4 (Web Text))

Max Activating Token Index: 634

Text #7

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.5400. Min Act: -0.0000

Data Index: 210558 (C4 (Web Text))

Max Activating Token Index: 893

Text #8

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.4396. Min Act: -0.0000

Data Index: 1025499 (C4 (Web Text))

Max Activating Token Index: 364

Text #9

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.3507. Min Act: -0.0000

Data Index: 1313220 (C4 (Web Text))

Max Activating Token Index: 582

Text #10

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.3975. Min Act: -0.0000

Data Index: 427520 (C4 (Web Text))

Max Activating Token Index: 890

Text #11

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.4312. Min Act: -0.0000

Data Index: 71407 (C4 (Web Text))

Max Activating Token Index: 605

Text #12

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.3380. Min Act: -0.0000

Data Index: 1319683 (C4 (Web Text))

Max Activating Token Index: 741

Text #13

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.2905. Min Act: -0.0000

Data Index: 605161 (C4 (Web Text))

Max Activating Token Index: 563

Text #14

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.3708. Min Act: -0.0000

Data Index: 1181157 (C4 (Web Text))

Max Activating Token Index: 469

Text #15

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.4118. Min Act: -0.0000

Data Index: 797477 (C4 (Web Text))

Max Activating Token Index: 918

Text #16

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.2815. Min Act: -0.0000

Data Index: 1081517 (C4 (Web Text))

Max Activating Token Index: 54

Text #17

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.3266. Min Act: -0.0000

Data Index: 170574 (C4 (Web Text))

Max Activating Token Index: 131

Text #18

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.2787. Min Act: -0.0000

Data Index: 760568 (C4 (Web Text))

Max Activating Token Index: 809

Text #19

Max Range: 1.6691. Min Range: -1.6691

Max Act: 1.3853. Min Act: 0.0000

Data Index: 1315512 (C4 (Web Text))

Max Activating Token Index: 675