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

Dataset: The Pile

Neuron 1993 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: 0.7357. Min Range: -0.7357

Max Act: 0.6370. Min Act: -0.0000

Data Index: 723484 (The Pile)

Max Activating Token Index: 633

Text #1

Max Range: 0.7357. Min Range: -0.7357

Max Act: 0.6612. Min Act: -0.0000

Data Index: 1192849 (The Pile)

Max Activating Token Index: 156

Text #2

Max Range: 0.7357. Min Range: -0.7357

Max Act: 0.4572. Min Act: -0.0000

Data Index: 1609573 (The Pile)

Max Activating Token Index: 623

Text #3

Max Range: 0.7357. Min Range: -0.7357

Max Act: 0.7357. Min Act: -0.0000

Data Index: 144762 (The Pile)

Max Activating Token Index: 505

Text #4

Max Range: 0.7357. Min Range: -0.7357

Max Act: 0.6215. Min Act: -0.0000

Data Index: 1081990 (The Pile)

Max Activating Token Index: 173

Text #5

Max Range: 0.7357. Min Range: -0.7357

Max Act: 0.5934. Min Act: -0.0000

Data Index: 981774 (The Pile)

Max Activating Token Index: 586

Text #6

Max Range: 0.7357. Min Range: -0.7357

Max Act: 0.5397. Min Act: -0.0000

Data Index: 892359 (The Pile)

Max Activating Token Index: 404

Text #7

Max Range: 0.7357. Min Range: -0.7357

Max Act: 0.4603. Min Act: -0.0000

Data Index: 48638 (The Pile)

Max Activating Token Index: 849

Text #8

Max Range: 0.7357. Min Range: -0.7357

Max Act: 0.4806. Min Act: -0.0000

Data Index: 1832333 (The Pile)

Max Activating Token Index: 417

Text #9

Max Range: 0.7357. Min Range: -0.7357

Max Act: 0.4571. Min Act: -0.0000

Data Index: 1953460 (The Pile)

Max Activating Token Index: 564

Text #10

Max Range: 0.7357. Min Range: -0.7357

Max Act: 0.4767. Min Act: -0.0000

Data Index: 1690975 (The Pile)

Max Activating Token Index: 856

Text #11

Max Range: 0.7357. Min Range: -0.7357

Max Act: 0.6642. Min Act: -0.0000

Data Index: 1277034 (The Pile)

Max Activating Token Index: 989

Text #12

Max Range: 0.7357. Min Range: -0.7357

Max Act: 0.4014. Min Act: -0.0000

Data Index: 1163291 (The Pile)

Max Activating Token Index: 747

Text #13

Max Range: 0.7357. Min Range: -0.7357

Max Act: 0.4247. Min Act: -0.0000

Data Index: 1343389 (The Pile)

Max Activating Token Index: 586

Text #14

Max Range: 0.7357. Min Range: -0.7357

Max Act: 0.4442. Min Act: -0.0000

Data Index: 1912857 (The Pile)

Max Activating Token Index: 35

Text #15

Max Range: 0.7357. Min Range: -0.7357

Max Act: 0.4399. Min Act: -0.0000

Data Index: 981361 (The Pile)

Max Activating Token Index: 406

Text #16

Max Range: 0.7357. Min Range: -0.7357

Max Act: 0.4371. Min Act: -0.0000

Data Index: 1042166 (The Pile)

Max Activating Token Index: 56

Text #17

Max Range: 0.7357. Min Range: -0.7357

Max Act: 0.4269. Min Act: -0.0000

Data Index: 1416457 (The Pile)

Max Activating Token Index: 737

Text #18

Max Range: 0.7357. Min Range: -0.7357

Max Act: 0.4662. Min Act: -0.0000

Data Index: 1579677 (The Pile)

Max Activating Token Index: 640

Text #19

Max Range: 0.7357. Min Range: -0.7357

Max Act: 0.4103. Min Act: -0.0000

Data Index: 159320 (The Pile)

Max Activating Token Index: 459