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

Dataset: The Pile

Neuron 3540 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.6037. Min Act: -0.0000

Data Index: 642722 (The Pile)

Max Activating Token Index: 47

Text #1

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.5282. Min Act: -0.0000

Data Index: 741261 (The Pile)

Max Activating Token Index: 414

Text #2

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.4913. Min Act: -0.0000

Data Index: 926773 (The Pile)

Max Activating Token Index: 69

Text #3

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.5010. Min Act: -0.0000

Data Index: 1558769 (The Pile)

Max Activating Token Index: 434

Text #4

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.4796. Min Act: -0.0000

Data Index: 1479215 (The Pile)

Max Activating Token Index: 244

Text #5

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.4768. Min Act: -0.0000

Data Index: 1668879 (The Pile)

Max Activating Token Index: 451

Text #6

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.4436. Min Act: -0.0000

Data Index: 898230 (The Pile)

Max Activating Token Index: 798

Text #7

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.4616. Min Act: -0.0000

Data Index: 1092675 (The Pile)

Max Activating Token Index: 905

Text #8

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.4699. Min Act: -0.0000

Data Index: 706025 (The Pile)

Max Activating Token Index: 443

Text #9

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.4645. Min Act: -0.0000

Data Index: 1949629 (The Pile)

Max Activating Token Index: 37

Text #10

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.4530. Min Act: -0.0000

Data Index: 1861560 (The Pile)

Max Activating Token Index: 15

Text #11

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.4789. Min Act: -0.0000

Data Index: 418809 (The Pile)

Max Activating Token Index: 16

Text #12

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.4658. Min Act: -0.0000

Data Index: 456090 (The Pile)

Max Activating Token Index: 485

Text #13

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.4408. Min Act: -0.0000

Data Index: 922059 (The Pile)

Max Activating Token Index: 785

Text #14

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.4576. Min Act: -0.0000

Data Index: 1565972 (The Pile)

Max Activating Token Index: 661

Text #15

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.4416. Min Act: -0.0000

Data Index: 554169 (The Pile)

Max Activating Token Index: 81

Text #16

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.4223. Min Act: -0.0000

Data Index: 1426398 (The Pile)

Max Activating Token Index: 662

Text #17

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.4682. Min Act: -0.0000

Data Index: 1543368 (The Pile)

Max Activating Token Index: 271

Text #18

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.4230. Min Act: -0.0000

Data Index: 627726 (The Pile)

Max Activating Token Index: 681

Text #19

Max Range: 0.6037. Min Range: -0.6037

Max Act: 0.4511. Min Act: -0.0000

Data Index: 894465 (The Pile)

Max Activating Token Index: 332