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

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

Neuron 6029 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.7838. Min Act: -0.0000

Data Index: 1098842 (C4 (Web Text))

Max Activating Token Index: 235

Text #1

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.8078. Min Act: -0.0000

Data Index: 965514 (C4 (Web Text))

Max Activating Token Index: 41

Text #2

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.7455. Min Act: -0.0000

Data Index: 523317 (C4 (Web Text))

Max Activating Token Index: 778

Text #3

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.6969. Min Act: -0.0000

Data Index: 1021335 (C4 (Web Text))

Max Activating Token Index: 637

Text #4

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.7200. Min Act: -0.0000

Data Index: 701203 (C4 (Web Text))

Max Activating Token Index: 234

Text #5

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.6657. Min Act: -0.0000

Data Index: 209969 (C4 (Web Text))

Max Activating Token Index: 980

Text #6

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.6894. Min Act: -0.0000

Data Index: 444342 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.6796. Min Act: -0.0000

Data Index: 61312 (C4 (Web Text))

Max Activating Token Index: 101

Text #8

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.7157. Min Act: -0.0000

Data Index: 793781 (C4 (Web Text))

Max Activating Token Index: 957

Text #9

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.6601. Min Act: -0.0000

Data Index: 1173051 (C4 (Web Text))

Max Activating Token Index: 268

Text #10

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.6129. Min Act: -0.0000

Data Index: 1020677 (C4 (Web Text))

Max Activating Token Index: 762

Text #11

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.6175. Min Act: -0.0000

Data Index: 485942 (C4 (Web Text))

Max Activating Token Index: 535

Text #12

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.6015. Min Act: -0.0000

Data Index: 449446 (C4 (Web Text))

Max Activating Token Index: 980

Text #13

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.5603. Min Act: -0.0000

Data Index: 1311897 (C4 (Web Text))

Max Activating Token Index: 647

Text #14

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.5530. Min Act: 0.0000

Data Index: 956749 (C4 (Web Text))

Max Activating Token Index: 1005

Text #15

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.5537. Min Act: -0.0000

Data Index: 252262 (C4 (Web Text))

Max Activating Token Index: 376

Text #16

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.5287. Min Act: 0.0001

Data Index: 874787 (C4 (Web Text))

Max Activating Token Index: 953

Text #17

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.5604. Min Act: -0.0000

Data Index: 512690 (C4 (Web Text))

Max Activating Token Index: 709

Text #18

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.4720. Min Act: -0.0000

Data Index: 492742 (C4 (Web Text))

Max Activating Token Index: 294

Text #19

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.5419. Min Act: -0.0000

Data Index: 1261410 (C4 (Web Text))

Max Activating Token Index: 816