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

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

Neuron 3603 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2960. Min Range: -2.2960

Max Act: 2.2960. Min Act: -0.0000

Data Index: 815922 (C4 (Web Text))

Max Activating Token Index: 564

Text #1

Max Range: 2.2960. Min Range: -2.2960

Max Act: 2.1928. Min Act: -0.0000

Data Index: 671012 (C4 (Web Text))

Max Activating Token Index: 729

Text #2

Max Range: 2.2960. Min Range: -2.2960

Max Act: 2.0504. Min Act: -0.0000

Data Index: 891702 (C4 (Web Text))

Max Activating Token Index: 62

Text #3

Max Range: 2.2960. Min Range: -2.2960

Max Act: 2.0451. Min Act: -0.0000

Data Index: 663060 (C4 (Web Text))

Max Activating Token Index: 286

Text #4

Max Range: 2.2960. Min Range: -2.2960

Max Act: 1.9848. Min Act: -0.0000

Data Index: 452453 (C4 (Web Text))

Max Activating Token Index: 1014

Text #5

Max Range: 2.2960. Min Range: -2.2960

Max Act: 1.8810. Min Act: -0.0000

Data Index: 1167857 (C4 (Web Text))

Max Activating Token Index: 82

Text #6

Max Range: 2.2960. Min Range: -2.2960

Max Act: 1.9283. Min Act: -0.0000

Data Index: 160710 (C4 (Web Text))

Max Activating Token Index: 731

Text #7

Max Range: 2.2960. Min Range: -2.2960

Max Act: 1.8360. Min Act: -0.0000

Data Index: 640061 (C4 (Web Text))

Max Activating Token Index: 297

Text #8

Max Range: 2.2960. Min Range: -2.2960

Max Act: 1.7180. Min Act: -0.0000

Data Index: 352393 (C4 (Web Text))

Max Activating Token Index: 73

Text #9

Max Range: 2.2960. Min Range: -2.2960

Max Act: 1.8085. Min Act: -0.0000

Data Index: 250222 (C4 (Web Text))

Max Activating Token Index: 55

Text #10

Max Range: 2.2960. Min Range: -2.2960

Max Act: 1.7306. Min Act: -0.0000

Data Index: 467074 (C4 (Web Text))

Max Activating Token Index: 499

Text #11

Max Range: 2.2960. Min Range: -2.2960

Max Act: 1.6702. Min Act: -0.0000

Data Index: 344977 (C4 (Web Text))

Max Activating Token Index: 967

Text #12

Max Range: 2.2960. Min Range: -2.2960

Max Act: 1.7577. Min Act: -0.0000

Data Index: 1340098 (C4 (Web Text))

Max Activating Token Index: 231

Text #13

Max Range: 2.2960. Min Range: -2.2960

Max Act: 1.6665. Min Act: -0.0000

Data Index: 576955 (C4 (Web Text))

Max Activating Token Index: 247

Text #14

Max Range: 2.2960. Min Range: -2.2960

Max Act: 1.6436. Min Act: -0.0000

Data Index: 1024067 (C4 (Web Text))

Max Activating Token Index: 367

Text #15

Max Range: 2.2960. Min Range: -2.2960

Max Act: 1.7425. Min Act: -0.0000

Data Index: 184552 (C4 (Web Text))

Max Activating Token Index: 605

Text #16

Max Range: 2.2960. Min Range: -2.2960

Max Act: 1.6808. Min Act: -0.0000

Data Index: 802733 (C4 (Web Text))

Max Activating Token Index: 461

Text #17

Max Range: 2.2960. Min Range: -2.2960

Max Act: 1.6549. Min Act: -0.0000

Data Index: 1353069 (C4 (Web Text))

Max Activating Token Index: 83

Text #18

Max Range: 2.2960. Min Range: -2.2960

Max Act: 1.5657. Min Act: -0.0000

Data Index: 170087 (C4 (Web Text))

Max Activating Token Index: 331

Text #19

Max Range: 2.2960. Min Range: -2.2960

Max Act: 1.5903. Min Act: -0.0000

Data Index: 1336727 (C4 (Web Text))

Max Activating Token Index: 317