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

Dataset: The Pile

Neuron 3315 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4660. Min Range: -0.4660

Max Act: 0.4660. Min Act: -0.0000

Data Index: 1634756 (The Pile)

Max Activating Token Index: 929

Text #1

Max Range: 0.4660. Min Range: -0.4660

Max Act: 0.4242. Min Act: -0.0000

Data Index: 1531308 (The Pile)

Max Activating Token Index: 613

Text #2

Max Range: 0.4660. Min Range: -0.4660

Max Act: 0.3980. Min Act: -0.0000

Data Index: 1493327 (The Pile)

Max Activating Token Index: 300

Text #3

Max Range: 0.4660. Min Range: -0.4660

Max Act: 0.3496. Min Act: -0.0000

Data Index: 77785 (The Pile)

Max Activating Token Index: 1004

Text #4

Max Range: 0.4660. Min Range: -0.4660

Max Act: 0.3372. Min Act: -0.0000

Data Index: 397140 (The Pile)

Max Activating Token Index: 25

Text #5

Max Range: 0.4660. Min Range: -0.4660

Max Act: 0.2629. Min Act: -0.0000

Data Index: 187108 (The Pile)

Max Activating Token Index: 642

Text #6

Max Range: 0.4660. Min Range: -0.4660

Max Act: 0.2616. Min Act: -0.0000

Data Index: 1722443 (The Pile)

Max Activating Token Index: 618

Text #7

Max Range: 0.4660. Min Range: -0.4660

Max Act: 0.2677. Min Act: -0.0000

Data Index: 378754 (The Pile)

Max Activating Token Index: 860

Text #8

Max Range: 0.4660. Min Range: -0.4660

Max Act: 0.2540. Min Act: -0.0000

Data Index: 931742 (The Pile)

Max Activating Token Index: 995

Text #9

Max Range: 0.4660. Min Range: -0.4660

Max Act: 0.2559. Min Act: -0.0000

Data Index: 527375 (The Pile)

Max Activating Token Index: 779

Text #10

Max Range: 0.4660. Min Range: -0.4660

Max Act: 0.2333. Min Act: -0.0000

Data Index: 81214 (The Pile)

Max Activating Token Index: 681

Text #11

Max Range: 0.4660. Min Range: -0.4660

Max Act: 0.2207. Min Act: -0.0000

Data Index: 598202 (The Pile)

Max Activating Token Index: 530

Text #12

Max Range: 0.4660. Min Range: -0.4660

Max Act: 0.2550. Min Act: -0.0000

Data Index: 1223811 (The Pile)

Max Activating Token Index: 897

Text #13

Max Range: 0.4660. Min Range: -0.4660

Max Act: 0.2351. Min Act: -0.0000

Data Index: 944186 (The Pile)

Max Activating Token Index: 967

Text #14

Max Range: 0.4660. Min Range: -0.4660

Max Act: 0.2365. Min Act: -0.0000

Data Index: 686897 (The Pile)

Max Activating Token Index: 988

Text #15

Max Range: 0.4660. Min Range: -0.4660

Max Act: 0.2327. Min Act: -0.0000

Data Index: 732614 (The Pile)

Max Activating Token Index: 1006

Text #16

Max Range: 0.4660. Min Range: -0.4660

Max Act: 0.2391. Min Act: -0.0000

Data Index: 501899 (The Pile)

Max Activating Token Index: 991

Text #17

Max Range: 0.4660. Min Range: -0.4660

Max Act: 0.2452. Min Act: -0.0000

Data Index: 3668 (The Pile)

Max Activating Token Index: 885

Text #18

Max Range: 0.4660. Min Range: -0.4660

Max Act: 0.2503. Min Act: -0.0000

Data Index: 986180 (The Pile)

Max Activating Token Index: 1021

Text #19

Max Range: 0.4660. Min Range: -0.4660

Max Act: 0.2284. Min Act: -0.0000

Data Index: 1837701 (The Pile)

Max Activating Token Index: 695