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

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

Neuron 2376 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.9225. Min Act: -0.0000

Data Index: 711103 (C4 (Web Text))

Max Activating Token Index: 341

Text #1

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.9805. Min Act: -0.0000

Data Index: 45299 (C4 (Web Text))

Max Activating Token Index: 132

Text #2

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.8493. Min Act: -0.0000

Data Index: 750009 (C4 (Web Text))

Max Activating Token Index: 872

Text #3

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.8059. Min Act: -0.0000

Data Index: 697759 (C4 (Web Text))

Max Activating Token Index: 603

Text #4

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.8512. Min Act: -0.0000

Data Index: 536551 (C4 (Web Text))

Max Activating Token Index: 378

Text #5

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.7970. Min Act: -0.0000

Data Index: 168312 (C4 (Web Text))

Max Activating Token Index: 560

Text #6

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.7505. Min Act: -0.0000

Data Index: 542031 (C4 (Web Text))

Max Activating Token Index: 1010

Text #7

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.7828. Min Act: -0.0000

Data Index: 840417 (C4 (Web Text))

Max Activating Token Index: 798

Text #8

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.6967. Min Act: -0.0000

Data Index: 725492 (C4 (Web Text))

Max Activating Token Index: 813

Text #9

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.6996. Min Act: -0.0000

Data Index: 279152 (C4 (Web Text))

Max Activating Token Index: 143

Text #10

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.6849. Min Act: -0.0000

Data Index: 355470 (C4 (Web Text))

Max Activating Token Index: 113

Text #11

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.6831. Min Act: -0.0000

Data Index: 373170 (C4 (Web Text))

Max Activating Token Index: 147

Text #12

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.6796. Min Act: -0.0000

Data Index: 158677 (C4 (Web Text))

Max Activating Token Index: 522

Text #13

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.6919. Min Act: -0.0000

Data Index: 507060 (C4 (Web Text))

Max Activating Token Index: 1017

Text #14

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.6948. Min Act: -0.0000

Data Index: 70339 (C4 (Web Text))

Max Activating Token Index: 741

Text #15

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.6530. Min Act: -0.0000

Data Index: 127436 (C4 (Web Text))

Max Activating Token Index: 101

Text #16

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.6261. Min Act: -0.0000

Data Index: 217927 (C4 (Web Text))

Max Activating Token Index: 230

Text #17

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.6631. Min Act: -0.0000

Data Index: 1133242 (C4 (Web Text))

Max Activating Token Index: 691

Text #18

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.6178. Min Act: -0.0000

Data Index: 1311972 (C4 (Web Text))

Max Activating Token Index: 881

Text #19

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.6388. Min Act: -0.0000

Data Index: 875287 (C4 (Web Text))

Max Activating Token Index: 726