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

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

Neuron 5051 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.7748. Min Range: -0.7748

Max Act: 0.7748. Min Act: -0.0002

Data Index: 395170 (C4 (Web Text))

Max Activating Token Index: 30

Text #1

Max Range: 0.7748. Min Range: -0.7748

Max Act: 0.7282. Min Act: -0.0002

Data Index: 999836 (C4 (Web Text))

Max Activating Token Index: 54

Text #2

Max Range: 0.7748. Min Range: -0.7748

Max Act: 0.6679. Min Act: -0.0002

Data Index: 225459 (C4 (Web Text))

Max Activating Token Index: 121

Text #3

Max Range: 0.7748. Min Range: -0.7748

Max Act: 0.6613. Min Act: -0.0002

Data Index: 1020323 (C4 (Web Text))

Max Activating Token Index: 168

Text #4

Max Range: 0.7748. Min Range: -0.7748

Max Act: 0.6387. Min Act: -0.0002

Data Index: 3133 (C4 (Web Text))

Max Activating Token Index: 10

Text #5

Max Range: 0.7748. Min Range: -0.7748

Max Act: 0.6286. Min Act: -0.0002

Data Index: 1246371 (C4 (Web Text))

Max Activating Token Index: 108

Text #6

Max Range: 0.7748. Min Range: -0.7748

Max Act: 0.6504. Min Act: -0.0002

Data Index: 1302145 (C4 (Web Text))

Max Activating Token Index: 71

Text #7

Max Range: 0.7748. Min Range: -0.7748

Max Act: 0.6409. Min Act: -0.0001

Data Index: 438920 (C4 (Web Text))

Max Activating Token Index: 47

Text #8

Max Range: 0.7748. Min Range: -0.7748

Max Act: 0.6381. Min Act: -0.0001

Data Index: 1196311 (C4 (Web Text))

Max Activating Token Index: 43

Text #9

Max Range: 0.7748. Min Range: -0.7748

Max Act: 0.6406. Min Act: -0.0002

Data Index: 1240180 (C4 (Web Text))

Max Activating Token Index: 65

Text #10

Max Range: 0.7748. Min Range: -0.7748

Max Act: 0.6278. Min Act: -0.0002

Data Index: 511516 (C4 (Web Text))

Max Activating Token Index: 69

Text #11

Max Range: 0.7748. Min Range: -0.7748

Max Act: 0.6122. Min Act: -0.0002

Data Index: 465645 (C4 (Web Text))

Max Activating Token Index: 335

Text #12

Max Range: 0.7748. Min Range: -0.7748

Max Act: 0.6172. Min Act: -0.0002

Data Index: 1124411 (C4 (Web Text))

Max Activating Token Index: 45

Text #13

Max Range: 0.7748. Min Range: -0.7748

Max Act: 0.6223. Min Act: -0.0002

Data Index: 518980 (C4 (Web Text))

Max Activating Token Index: 56

Text #14

Max Range: 0.7748. Min Range: -0.7748

Max Act: 0.6191. Min Act: -0.0002

Data Index: 1070819 (C4 (Web Text))

Max Activating Token Index: 608

Text #15

Max Range: 0.7748. Min Range: -0.7748

Max Act: 0.5905. Min Act: -0.0002

Data Index: 246522 (C4 (Web Text))

Max Activating Token Index: 459

Text #16

Max Range: 0.7748. Min Range: -0.7748

Max Act: 0.6035. Min Act: -0.0002

Data Index: 850736 (C4 (Web Text))

Max Activating Token Index: 26

Text #17

Max Range: 0.7748. Min Range: -0.7748

Max Act: 0.5977. Min Act: -0.0002

Data Index: 642935 (C4 (Web Text))

Max Activating Token Index: 116

Text #18

Max Range: 0.7748. Min Range: -0.7748

Max Act: 0.5980. Min Act: -0.0001

Data Index: 264250 (C4 (Web Text))

Max Activating Token Index: 171

Text #19

Max Range: 0.7748. Min Range: -0.7748

Max Act: 0.5859. Min Act: -0.0002

Data Index: 317217 (C4 (Web Text))

Max Activating Token Index: 733