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

Dataset: The Pile

Neuron 2848 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4201. Min Range: -1.4201

Max Act: 1.4201. Min Act: -0.0000

Data Index: 385370 (The Pile)

Max Activating Token Index: 569

Text #1

Max Range: 1.4201. Min Range: -1.4201

Max Act: 1.2024. Min Act: -0.0000

Data Index: 668405 (The Pile)

Max Activating Token Index: 896

Text #2

Max Range: 1.4201. Min Range: -1.4201

Max Act: 1.1281. Min Act: -0.0000

Data Index: 337989 (The Pile)

Max Activating Token Index: 597

Text #3

Max Range: 1.4201. Min Range: -1.4201

Max Act: 1.1360. Min Act: -0.0000

Data Index: 355275 (The Pile)

Max Activating Token Index: 517

Text #4

Max Range: 1.4201. Min Range: -1.4201

Max Act: 1.0314. Min Act: -0.0000

Data Index: 1919222 (The Pile)

Max Activating Token Index: 944

Text #5

Max Range: 1.4201. Min Range: -1.4201

Max Act: 1.0416. Min Act: -0.0000

Data Index: 785125 (The Pile)

Max Activating Token Index: 914

Text #6

Max Range: 1.4201. Min Range: -1.4201

Max Act: 0.9454. Min Act: -0.0000

Data Index: 1725619 (The Pile)

Max Activating Token Index: 380

Text #7

Max Range: 1.4201. Min Range: -1.4201

Max Act: 1.0774. Min Act: -0.0000

Data Index: 939652 (The Pile)

Max Activating Token Index: 13

Text #8

Max Range: 1.4201. Min Range: -1.4201

Max Act: 0.9620. Min Act: -0.0000

Data Index: 1873953 (The Pile)

Max Activating Token Index: 32

Text #9

Max Range: 1.4201. Min Range: -1.4201

Max Act: 0.9498. Min Act: -0.0000

Data Index: 1069330 (The Pile)

Max Activating Token Index: 357

Text #10

Max Range: 1.4201. Min Range: -1.4201

Max Act: 1.0141. Min Act: -0.0000

Data Index: 1653033 (The Pile)

Max Activating Token Index: 486

Text #11

Max Range: 1.4201. Min Range: -1.4201

Max Act: 1.0942. Min Act: -0.0000

Data Index: 1225598 (The Pile)

Max Activating Token Index: 528

Text #12

Max Range: 1.4201. Min Range: -1.4201

Max Act: 1.0428. Min Act: -0.0000

Data Index: 1249029 (The Pile)

Max Activating Token Index: 829

Text #13

Max Range: 1.4201. Min Range: -1.4201

Max Act: 0.9512. Min Act: -0.0000

Data Index: 13876 (The Pile)

Max Activating Token Index: 790

Text #14

Max Range: 1.4201. Min Range: -1.4201

Max Act: 0.9783. Min Act: -0.0000

Data Index: 606247 (The Pile)

Max Activating Token Index: 655

Text #15

Max Range: 1.4201. Min Range: -1.4201

Max Act: 0.9480. Min Act: -0.0000

Data Index: 1072489 (The Pile)

Max Activating Token Index: 710

Text #16

Max Range: 1.4201. Min Range: -1.4201

Max Act: 0.9344. Min Act: -0.0000

Data Index: 1441395 (The Pile)

Max Activating Token Index: 202

Text #17

Max Range: 1.4201. Min Range: -1.4201

Max Act: 0.9338. Min Act: -0.0000

Data Index: 1704525 (The Pile)

Max Activating Token Index: 380

Text #18

Max Range: 1.4201. Min Range: -1.4201

Max Act: 0.9622. Min Act: -0.0000

Data Index: 1990136 (The Pile)

Max Activating Token Index: 297

Text #19

Max Range: 1.4201. Min Range: -1.4201

Max Act: 0.9312. Min Act: -0.0000

Data Index: 1000912 (The Pile)

Max Activating Token Index: 393