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

Dataset: The Pile

Neuron 1800 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0594. Min Act: 0.0000

Data Index: 438569 (The Pile)

Max Activating Token Index: 9

Text #1

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0563. Min Act: -0.0000

Data Index: 753778 (The Pile)

Max Activating Token Index: 302

Text #2

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0550. Min Act: -0.0000

Data Index: 1214263 (The Pile)

Max Activating Token Index: 9

Text #3

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0542. Min Act: 0.0000

Data Index: 768998 (The Pile)

Max Activating Token Index: 30

Text #4

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0507. Min Act: -0.0000

Data Index: 188640 (The Pile)

Max Activating Token Index: 24

Text #5

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0489. Min Act: 0.0000

Data Index: 1071462 (The Pile)

Max Activating Token Index: 9

Text #6

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0501. Min Act: -0.0000

Data Index: 217995 (The Pile)

Max Activating Token Index: 41

Text #7

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0499. Min Act: 0.0000

Data Index: 1589976 (The Pile)

Max Activating Token Index: 71

Text #8

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0495. Min Act: -0.0000

Data Index: 1875964 (The Pile)

Max Activating Token Index: 9

Text #9

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0486. Min Act: 0.0000

Data Index: 912963 (The Pile)

Max Activating Token Index: 63

Text #10

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0482. Min Act: 0.0000

Data Index: 797554 (The Pile)

Max Activating Token Index: 24

Text #11

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0478. Min Act: 0.0000

Data Index: 1572314 (The Pile)

Max Activating Token Index: 24

Text #12

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0475. Min Act: 0.0000

Data Index: 531548 (The Pile)

Max Activating Token Index: 36

Text #13

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0475. Min Act: -0.0000

Data Index: 995328 (The Pile)

Max Activating Token Index: 24

Text #14

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0474. Min Act: 0.0000

Data Index: 538639 (The Pile)

Max Activating Token Index: 173

Text #15

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0472. Min Act: 0.0000

Data Index: 717582 (The Pile)

Max Activating Token Index: 7

Text #16

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0470. Min Act: -0.0000

Data Index: 1141458 (The Pile)

Max Activating Token Index: 32

Text #17

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0467. Min Act: -0.0000

Data Index: 654621 (The Pile)

Max Activating Token Index: 86

Text #18

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0462. Min Act: -0.0000

Data Index: 559540 (The Pile)

Max Activating Token Index: 8

Text #19

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0462. Min Act: -0.0000

Data Index: 1221912 (The Pile)

Max Activating Token Index: 30