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

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

Neuron 3948 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0927. Min Range: -2.0927

Max Act: 2.0642. Min Act: -0.0000

Data Index: 106161 (C4 (Web Text))

Max Activating Token Index: 765

Text #1

Max Range: 2.0927. Min Range: -2.0927

Max Act: 1.9497. Min Act: -0.0000

Data Index: 181972 (C4 (Web Text))

Max Activating Token Index: 356

Text #2

Max Range: 2.0927. Min Range: -2.0927

Max Act: 2.0927. Min Act: -0.0000

Data Index: 537407 (C4 (Web Text))

Max Activating Token Index: 64

Text #3

Max Range: 2.0927. Min Range: -2.0927

Max Act: 1.9334. Min Act: -0.0000

Data Index: 1142336 (C4 (Web Text))

Max Activating Token Index: 547

Text #4

Max Range: 2.0927. Min Range: -2.0927

Max Act: 1.8063. Min Act: -0.0000

Data Index: 964069 (C4 (Web Text))

Max Activating Token Index: 753

Text #5

Max Range: 2.0927. Min Range: -2.0927

Max Act: 1.8212. Min Act: -0.0000

Data Index: 930757 (C4 (Web Text))

Max Activating Token Index: 859

Text #6

Max Range: 2.0927. Min Range: -2.0927

Max Act: 1.6879. Min Act: -0.0000

Data Index: 879718 (C4 (Web Text))

Max Activating Token Index: 67

Text #7

Max Range: 2.0927. Min Range: -2.0927

Max Act: 1.6730. Min Act: -0.0000

Data Index: 629642 (C4 (Web Text))

Max Activating Token Index: 43

Text #8

Max Range: 2.0927. Min Range: -2.0927

Max Act: 1.6626. Min Act: -0.0000

Data Index: 355978 (C4 (Web Text))

Max Activating Token Index: 43

Text #9

Max Range: 2.0927. Min Range: -2.0927

Max Act: 1.6512. Min Act: -0.0000

Data Index: 275937 (C4 (Web Text))

Max Activating Token Index: 72

Text #10

Max Range: 2.0927. Min Range: -2.0927

Max Act: 1.5564. Min Act: -0.0000

Data Index: 940603 (C4 (Web Text))

Max Activating Token Index: 263

Text #11

Max Range: 2.0927. Min Range: -2.0927

Max Act: 1.6474. Min Act: -0.0000

Data Index: 770893 (C4 (Web Text))

Max Activating Token Index: 107

Text #12

Max Range: 2.0927. Min Range: -2.0927

Max Act: 1.6397. Min Act: -0.0000

Data Index: 916838 (C4 (Web Text))

Max Activating Token Index: 94

Text #13

Max Range: 2.0927. Min Range: -2.0927

Max Act: 1.6360. Min Act: -0.0000

Data Index: 582787 (C4 (Web Text))

Max Activating Token Index: 668

Text #14

Max Range: 2.0927. Min Range: -2.0927

Max Act: 1.7288. Min Act: -0.0000

Data Index: 348985 (C4 (Web Text))

Max Activating Token Index: 638

Text #15

Max Range: 2.0927. Min Range: -2.0927

Max Act: 1.6340. Min Act: -0.0000

Data Index: 765471 (C4 (Web Text))

Max Activating Token Index: 50

Text #16

Max Range: 2.0927. Min Range: -2.0927

Max Act: 1.6294. Min Act: -0.0000

Data Index: 1352645 (C4 (Web Text))

Max Activating Token Index: 532

Text #17

Max Range: 2.0927. Min Range: -2.0927

Max Act: 1.6249. Min Act: -0.0000

Data Index: 1133245 (C4 (Web Text))

Max Activating Token Index: 52

Text #18

Max Range: 2.0927. Min Range: -2.0927

Max Act: 1.4413. Min Act: -0.0000

Data Index: 178881 (C4 (Web Text))

Max Activating Token Index: 199

Text #19

Max Range: 2.0927. Min Range: -2.0927

Max Act: 1.6064. Min Act: -0.0000

Data Index: 1162380 (C4 (Web Text))

Max Activating Token Index: 946