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

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

Neuron 3425 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.1185. Min Act: -0.0000

Data Index: 312986 (C4 (Web Text))

Max Activating Token Index: 205

Text #1

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.1024. Min Act: -0.0000

Data Index: 862223 (C4 (Web Text))

Max Activating Token Index: 801

Text #2

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0755. Min Act: -0.0000

Data Index: 1034933 (C4 (Web Text))

Max Activating Token Index: 620

Text #3

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0813. Min Act: -0.0001

Data Index: 1265632 (C4 (Web Text))

Max Activating Token Index: 34

Text #4

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0796. Min Act: -0.0000

Data Index: 1314166 (C4 (Web Text))

Max Activating Token Index: 216

Text #5

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0728. Min Act: -0.0000

Data Index: 131734 (C4 (Web Text))

Max Activating Token Index: 886

Text #6

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0678. Min Act: -0.0000

Data Index: 283548 (C4 (Web Text))

Max Activating Token Index: 459

Text #7

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0660. Min Act: -0.0000

Data Index: 531927 (C4 (Web Text))

Max Activating Token Index: 594

Text #8

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0706. Min Act: -0.0000

Data Index: 942895 (C4 (Web Text))

Max Activating Token Index: 23

Text #9

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0705. Min Act: -0.0000

Data Index: 584697 (C4 (Web Text))

Max Activating Token Index: 366

Text #10

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0752. Min Act: -0.0000

Data Index: 1382279 (Python Code)

Max Activating Token Index: 26

Text #11

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0656. Min Act: -0.0000

Data Index: 1079061 (C4 (Web Text))

Max Activating Token Index: 295

Text #12

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0716. Min Act: -0.0000

Data Index: 1343381 (C4 (Web Text))

Max Activating Token Index: 326

Text #13

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0683. Min Act: -0.0000

Data Index: 90262 (C4 (Web Text))

Max Activating Token Index: 567

Text #14

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0555. Min Act: -0.0000

Data Index: 459232 (C4 (Web Text))

Max Activating Token Index: 389

Text #15

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0577. Min Act: -0.0000

Data Index: 167712 (C4 (Web Text))

Max Activating Token Index: 11

Text #16

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0524. Min Act: -0.0000

Data Index: 673122 (C4 (Web Text))

Max Activating Token Index: 478

Text #17

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0633. Min Act: -0.0000

Data Index: 982606 (C4 (Web Text))

Max Activating Token Index: 935

Text #18

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0620. Min Act: -0.0000

Data Index: 765441 (C4 (Web Text))

Max Activating Token Index: 526

Text #19

Max Range: 0.1185. Min Range: -0.1185

Max Act: 0.0572. Min Act: -0.0000

Data Index: 1309602 (C4 (Web Text))

Max Activating Token Index: 878