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

Dataset: The Pile

Neuron 2973 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.9943. Min Range: -0.9943

Max Act: 0.9943. Min Act: -0.0000

Data Index: 65981 (The Pile)

Max Activating Token Index: 415

Text #1

Max Range: 0.9943. Min Range: -0.9943

Max Act: 0.9260. Min Act: -0.0000

Data Index: 1688768 (The Pile)

Max Activating Token Index: 61

Text #2

Max Range: 0.9943. Min Range: -0.9943

Max Act: 0.8846. Min Act: -0.0000

Data Index: 1386900 (The Pile)

Max Activating Token Index: 641

Text #3

Max Range: 0.9943. Min Range: -0.9943

Max Act: 0.8684. Min Act: -0.0000

Data Index: 770529 (The Pile)

Max Activating Token Index: 662

Text #4

Max Range: 0.9943. Min Range: -0.9943

Max Act: 0.8727. Min Act: -0.0000

Data Index: 483916 (The Pile)

Max Activating Token Index: 911

Text #5

Max Range: 0.9943. Min Range: -0.9943

Max Act: 0.8433. Min Act: -0.0000

Data Index: 867222 (The Pile)

Max Activating Token Index: 725

Text #6

Max Range: 0.9943. Min Range: -0.9943

Max Act: 0.8153. Min Act: -0.0000

Data Index: 1508027 (The Pile)

Max Activating Token Index: 991

Text #7

Max Range: 0.9943. Min Range: -0.9943

Max Act: 0.7908. Min Act: -0.0000

Data Index: 447228 (The Pile)

Max Activating Token Index: 548

Text #8

Max Range: 0.9943. Min Range: -0.9943

Max Act: 0.8656. Min Act: -0.0000

Data Index: 837198 (The Pile)

Max Activating Token Index: 538

Text #9

Max Range: 0.9943. Min Range: -0.9943

Max Act: 0.7908. Min Act: -0.0000

Data Index: 1313900 (The Pile)

Max Activating Token Index: 376

Text #10

Max Range: 0.9943. Min Range: -0.9943

Max Act: 0.8099. Min Act: -0.0000

Data Index: 673493 (The Pile)

Max Activating Token Index: 130

Text #11

Max Range: 0.9943. Min Range: -0.9943

Max Act: 0.7473. Min Act: -0.0000

Data Index: 1443877 (The Pile)

Max Activating Token Index: 490

Text #12

Max Range: 0.9943. Min Range: -0.9943

Max Act: 0.7370. Min Act: -0.0000

Data Index: 215297 (The Pile)

Max Activating Token Index: 825

Text #13

Max Range: 0.9943. Min Range: -0.9943

Max Act: 0.6788. Min Act: -0.0000

Data Index: 1433726 (The Pile)

Max Activating Token Index: 940

Text #14

Max Range: 0.9943. Min Range: -0.9943

Max Act: 0.7029. Min Act: -0.0000

Data Index: 1161759 (The Pile)

Max Activating Token Index: 816

Text #15

Max Range: 0.9943. Min Range: -0.9943

Max Act: 0.7171. Min Act: -0.0000

Data Index: 1085914 (The Pile)

Max Activating Token Index: 134

Text #16

Max Range: 0.9943. Min Range: -0.9943

Max Act: 0.6904. Min Act: -0.0000

Data Index: 287855 (The Pile)

Max Activating Token Index: 314

Text #17

Max Range: 0.9943. Min Range: -0.9943

Max Act: 0.6328. Min Act: -0.0000

Data Index: 1458636 (The Pile)

Max Activating Token Index: 643

Text #18

Max Range: 0.9943. Min Range: -0.9943

Max Act: 0.6836. Min Act: -0.0000

Data Index: 1012398 (The Pile)

Max Activating Token Index: 134

Text #19

Max Range: 0.9943. Min Range: -0.9943

Max Act: 0.6932. Min Act: -0.0000

Data Index: 1143203 (The Pile)

Max Activating Token Index: 733