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

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

Neuron 3921 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: 2.3294. Min Range: -2.3294

Max Act: 2.3294. Min Act: -0.0000

Data Index: 156325 (C4 (Web Text))

Max Activating Token Index: 789

Text #1

Max Range: 2.3294. Min Range: -2.3294

Max Act: 2.3142. Min Act: -0.0000

Data Index: 1298815 (C4 (Web Text))

Max Activating Token Index: 883

Text #2

Max Range: 2.3294. Min Range: -2.3294

Max Act: 2.2417. Min Act: -0.0000

Data Index: 1354653 (C4 (Web Text))

Max Activating Token Index: 1017

Text #3

Max Range: 2.3294. Min Range: -2.3294

Max Act: 2.1209. Min Act: -0.0000

Data Index: 810034 (C4 (Web Text))

Max Activating Token Index: 423

Text #4

Max Range: 2.3294. Min Range: -2.3294

Max Act: 2.0921. Min Act: -0.0000

Data Index: 374099 (C4 (Web Text))

Max Activating Token Index: 24

Text #5

Max Range: 2.3294. Min Range: -2.3294

Max Act: 2.0369. Min Act: -0.0000

Data Index: 893091 (C4 (Web Text))

Max Activating Token Index: 86

Text #6

Max Range: 2.3294. Min Range: -2.3294

Max Act: 2.0311. Min Act: -0.0000

Data Index: 255712 (C4 (Web Text))

Max Activating Token Index: 88

Text #7

Max Range: 2.3294. Min Range: -2.3294

Max Act: 2.0359. Min Act: 0.0000

Data Index: 1109917 (C4 (Web Text))

Max Activating Token Index: 230

Text #8

Max Range: 2.3294. Min Range: -2.3294

Max Act: 2.0268. Min Act: -0.0000

Data Index: 662847 (C4 (Web Text))

Max Activating Token Index: 539

Text #9

Max Range: 2.3294. Min Range: -2.3294

Max Act: 1.9976. Min Act: 0.0000

Data Index: 967277 (C4 (Web Text))

Max Activating Token Index: 106

Text #10

Max Range: 2.3294. Min Range: -2.3294

Max Act: 1.9930. Min Act: -0.0000

Data Index: 1427771 (Python Code)

Max Activating Token Index: 636

Text #11

Max Range: 2.3294. Min Range: -2.3294

Max Act: 1.9727. Min Act: -0.0000

Data Index: 867127 (C4 (Web Text))

Max Activating Token Index: 131

Text #12

Max Range: 2.3294. Min Range: -2.3294

Max Act: 1.9547. Min Act: -0.0000

Data Index: 427549 (C4 (Web Text))

Max Activating Token Index: 998

Text #13

Max Range: 2.3294. Min Range: -2.3294

Max Act: 2.0750. Min Act: -0.0000

Data Index: 87357 (C4 (Web Text))

Max Activating Token Index: 569

Text #14

Max Range: 2.3294. Min Range: -2.3294

Max Act: 1.8388. Min Act: -0.0000

Data Index: 88590 (C4 (Web Text))

Max Activating Token Index: 271

Text #15

Max Range: 2.3294. Min Range: -2.3294

Max Act: 2.0230. Min Act: -0.0000

Data Index: 1254782 (C4 (Web Text))

Max Activating Token Index: 889

Text #16

Max Range: 2.3294. Min Range: -2.3294

Max Act: 1.8052. Min Act: -0.0000

Data Index: 9720 (C4 (Web Text))

Max Activating Token Index: 851

Text #17

Max Range: 2.3294. Min Range: -2.3294

Max Act: 1.8904. Min Act: -0.0000

Data Index: 302712 (C4 (Web Text))

Max Activating Token Index: 679

Text #18

Max Range: 2.3294. Min Range: -2.3294

Max Act: 1.8784. Min Act: 0.0000

Data Index: 271199 (C4 (Web Text))

Max Activating Token Index: 732

Text #19

Max Range: 2.3294. Min Range: -2.3294

Max Act: 1.8813. Min Act: -0.0000

Data Index: 502622 (C4 (Web Text))

Max Activating Token Index: 710