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

Dataset: The Pile

Neuron 4643 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: 0.9415. Min Range: -0.9415

Max Act: 0.9415. Min Act: -0.0000

Data Index: 869256 (The Pile)

Max Activating Token Index: 660

Text #1

Max Range: 0.9415. Min Range: -0.9415

Max Act: 0.8961. Min Act: -0.0000

Data Index: 834795 (The Pile)

Max Activating Token Index: 688

Text #2

Max Range: 0.9415. Min Range: -0.9415

Max Act: 0.8538. Min Act: -0.0000

Data Index: 1263671 (The Pile)

Max Activating Token Index: 10

Text #3

Max Range: 0.9415. Min Range: -0.9415

Max Act: 0.7858. Min Act: -0.0000

Data Index: 254896 (The Pile)

Max Activating Token Index: 237

Text #4

Max Range: 0.9415. Min Range: -0.9415

Max Act: 0.7731. Min Act: -0.0000

Data Index: 490484 (The Pile)

Max Activating Token Index: 555

Text #5

Max Range: 0.9415. Min Range: -0.9415

Max Act: 0.7757. Min Act: -0.0000

Data Index: 619348 (The Pile)

Max Activating Token Index: 9

Text #6

Max Range: 0.9415. Min Range: -0.9415

Max Act: 0.7359. Min Act: -0.0000

Data Index: 1351312 (The Pile)

Max Activating Token Index: 773

Text #7

Max Range: 0.9415. Min Range: -0.9415

Max Act: 0.7230. Min Act: -0.0000

Data Index: 1821590 (The Pile)

Max Activating Token Index: 496

Text #8

Max Range: 0.9415. Min Range: -0.9415

Max Act: 0.6401. Min Act: -0.0000

Data Index: 1027714 (The Pile)

Max Activating Token Index: 777

Text #9

Max Range: 0.9415. Min Range: -0.9415

Max Act: 0.7870. Min Act: -0.0000

Data Index: 309673 (The Pile)

Max Activating Token Index: 793

Text #10

Max Range: 0.9415. Min Range: -0.9415

Max Act: 0.6500. Min Act: -0.0000

Data Index: 1262738 (The Pile)

Max Activating Token Index: 345

Text #11

Max Range: 0.9415. Min Range: -0.9415

Max Act: 0.7050. Min Act: -0.0000

Data Index: 1301901 (The Pile)

Max Activating Token Index: 369

Text #12

Max Range: 0.9415. Min Range: -0.9415

Max Act: 0.6511. Min Act: -0.0000

Data Index: 507553 (The Pile)

Max Activating Token Index: 16

Text #13

Max Range: 0.9415. Min Range: -0.9415

Max Act: 0.6940. Min Act: -0.0000

Data Index: 588398 (The Pile)

Max Activating Token Index: 20

Text #14

Max Range: 0.9415. Min Range: -0.9415

Max Act: 0.6999. Min Act: -0.0000

Data Index: 1399106 (The Pile)

Max Activating Token Index: 68

Text #15

Max Range: 0.9415. Min Range: -0.9415

Max Act: 0.6812. Min Act: -0.0000

Data Index: 1497498 (The Pile)

Max Activating Token Index: 355

Text #16

Max Range: 0.9415. Min Range: -0.9415

Max Act: 0.6327. Min Act: -0.0000

Data Index: 1966815 (The Pile)

Max Activating Token Index: 542

Text #17

Max Range: 0.9415. Min Range: -0.9415

Max Act: 0.6960. Min Act: -0.0000

Data Index: 1458139 (The Pile)

Max Activating Token Index: 8

Text #18

Max Range: 0.9415. Min Range: -0.9415

Max Act: 0.6671. Min Act: -0.0000

Data Index: 1730878 (The Pile)

Max Activating Token Index: 240

Text #19

Max Range: 0.9415. Min Range: -0.9415

Max Act: 0.6898. Min Act: -0.0000

Data Index: 179894 (The Pile)

Max Activating Token Index: 510