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

Dataset: The Pile

Neuron 3872 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7916. Min Range: -0.7916

Max Act: 0.7279. Min Act: -0.0000

Data Index: 1394888 (The Pile)

Max Activating Token Index: 618

Text #1

Max Range: 0.7916. Min Range: -0.7916

Max Act: 0.7916. Min Act: -0.0000

Data Index: 456395 (The Pile)

Max Activating Token Index: 27

Text #2

Max Range: 0.7916. Min Range: -0.7916

Max Act: 0.5724. Min Act: -0.0000

Data Index: 471013 (The Pile)

Max Activating Token Index: 120

Text #3

Max Range: 0.7916. Min Range: -0.7916

Max Act: 0.5887. Min Act: -0.0000

Data Index: 240340 (The Pile)

Max Activating Token Index: 896

Text #4

Max Range: 0.7916. Min Range: -0.7916

Max Act: 0.5457. Min Act: -0.0000

Data Index: 1909379 (The Pile)

Max Activating Token Index: 126

Text #5

Max Range: 0.7916. Min Range: -0.7916

Max Act: 0.5385. Min Act: -0.0000

Data Index: 822236 (The Pile)

Max Activating Token Index: 800

Text #6

Max Range: 0.7916. Min Range: -0.7916

Max Act: 0.5492. Min Act: -0.0000

Data Index: 860826 (The Pile)

Max Activating Token Index: 164

Text #7

Max Range: 0.7916. Min Range: -0.7916

Max Act: 0.5262. Min Act: -0.0000

Data Index: 35301 (The Pile)

Max Activating Token Index: 465

Text #8

Max Range: 0.7916. Min Range: -0.7916

Max Act: 0.5147. Min Act: -0.0000

Data Index: 1131552 (The Pile)

Max Activating Token Index: 221

Text #9

Max Range: 0.7916. Min Range: -0.7916

Max Act: 0.5187. Min Act: -0.0000

Data Index: 868247 (The Pile)

Max Activating Token Index: 758

Text #10

Max Range: 0.7916. Min Range: -0.7916

Max Act: 0.4509. Min Act: -0.0000

Data Index: 1427189 (The Pile)

Max Activating Token Index: 74

Text #11

Max Range: 0.7916. Min Range: -0.7916

Max Act: 0.4683. Min Act: -0.0000

Data Index: 577747 (The Pile)

Max Activating Token Index: 311

Text #12

Max Range: 0.7916. Min Range: -0.7916

Max Act: 0.4624. Min Act: -0.0000

Data Index: 1349312 (The Pile)

Max Activating Token Index: 201

Text #13

Max Range: 0.7916. Min Range: -0.7916

Max Act: 0.4672. Min Act: -0.0000

Data Index: 1814463 (The Pile)

Max Activating Token Index: 553

Text #14

Max Range: 0.7916. Min Range: -0.7916

Max Act: 0.4393. Min Act: -0.0000

Data Index: 969094 (The Pile)

Max Activating Token Index: 459

Text #15

Max Range: 0.7916. Min Range: -0.7916

Max Act: 0.4467. Min Act: -0.0000

Data Index: 1789091 (The Pile)

Max Activating Token Index: 513

Text #16

Max Range: 0.7916. Min Range: -0.7916

Max Act: 0.4801. Min Act: -0.0000

Data Index: 1199488 (The Pile)

Max Activating Token Index: 169

Text #17

Max Range: 0.7916. Min Range: -0.7916

Max Act: 0.4625. Min Act: -0.0000

Data Index: 210993 (The Pile)

Max Activating Token Index: 679

Text #18

Max Range: 0.7916. Min Range: -0.7916

Max Act: 0.4215. Min Act: -0.0000

Data Index: 700374 (The Pile)

Max Activating Token Index: 513

Text #19

Max Range: 0.7916. Min Range: -0.7916

Max Act: 0.4910. Min Act: -0.0000

Data Index: 1811477 (The Pile)

Max Activating Token Index: 848