Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1629 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.5103. Min Act: -0.0000

Data Index: 1542317 (The Pile)

Max Activating Token Index: 694

Text #1

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.4955. Min Act: -0.0000

Data Index: 262090 (The Pile)

Max Activating Token Index: 605

Text #2

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.5202. Min Act: -0.0000

Data Index: 790863 (The Pile)

Max Activating Token Index: 692

Text #3

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.5143. Min Act: -0.0000

Data Index: 1476835 (The Pile)

Max Activating Token Index: 416

Text #4

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.4922. Min Act: -0.0000

Data Index: 1145686 (The Pile)

Max Activating Token Index: 945

Text #5

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.4536. Min Act: -0.0000

Data Index: 879555 (The Pile)

Max Activating Token Index: 499

Text #6

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.4143. Min Act: 0.0001

Data Index: 1405540 (The Pile)

Max Activating Token Index: 74

Text #7

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.4356. Min Act: -0.0000

Data Index: 317529 (The Pile)

Max Activating Token Index: 703

Text #8

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.4030. Min Act: -0.0000

Data Index: 1369386 (The Pile)

Max Activating Token Index: 936

Text #9

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.4331. Min Act: -0.0000

Data Index: 999135 (The Pile)

Max Activating Token Index: 308

Text #10

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.3644. Min Act: -0.0000

Data Index: 598878 (The Pile)

Max Activating Token Index: 558

Text #11

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.4065. Min Act: -0.0000

Data Index: 691264 (The Pile)

Max Activating Token Index: 323

Text #12

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.3771. Min Act: -0.0000

Data Index: 265651 (The Pile)

Max Activating Token Index: 960

Text #13

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.4587. Min Act: -0.0000

Data Index: 1663504 (The Pile)

Max Activating Token Index: 739

Text #14

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.3897. Min Act: -0.0000

Data Index: 47924 (The Pile)

Max Activating Token Index: 161

Text #15

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.3583. Min Act: -0.0000

Data Index: 1948387 (The Pile)

Max Activating Token Index: 977

Text #16

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.3929. Min Act: -0.0000

Data Index: 1548935 (The Pile)

Max Activating Token Index: 251

Text #17

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.3774. Min Act: -0.0000

Data Index: 1381539 (The Pile)

Max Activating Token Index: 804

Text #18

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.3459. Min Act: -0.0000

Data Index: 177716 (The Pile)

Max Activating Token Index: 781

Text #19

Max Range: 0.5202. Min Range: -0.5202

Max Act: 0.4007. Min Act: -0.0000

Data Index: 1437557 (The Pile)

Max Activating Token Index: 950