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

Dataset: The Pile

Neuron 1960 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: 1.4078. Min Range: -1.4078

Max Act: 1.4078. Min Act: -0.0000

Data Index: 655386 (The Pile)

Max Activating Token Index: 55

Text #1

Max Range: 1.4078. Min Range: -1.4078

Max Act: 1.3266. Min Act: -0.0000

Data Index: 1973534 (The Pile)

Max Activating Token Index: 634

Text #2

Max Range: 1.4078. Min Range: -1.4078

Max Act: 1.2147. Min Act: -0.0000

Data Index: 1717275 (The Pile)

Max Activating Token Index: 303

Text #3

Max Range: 1.4078. Min Range: -1.4078

Max Act: 1.2571. Min Act: -0.0000

Data Index: 1097882 (The Pile)

Max Activating Token Index: 565

Text #4

Max Range: 1.4078. Min Range: -1.4078

Max Act: 1.1671. Min Act: -0.0000

Data Index: 1301061 (The Pile)

Max Activating Token Index: 363

Text #5

Max Range: 1.4078. Min Range: -1.4078

Max Act: 1.1578. Min Act: -0.0000

Data Index: 1793215 (The Pile)

Max Activating Token Index: 226

Text #6

Max Range: 1.4078. Min Range: -1.4078

Max Act: 1.1477. Min Act: -0.0000

Data Index: 1156446 (The Pile)

Max Activating Token Index: 119

Text #7

Max Range: 1.4078. Min Range: -1.4078

Max Act: 1.0714. Min Act: -0.0000

Data Index: 328851 (The Pile)

Max Activating Token Index: 1002

Text #8

Max Range: 1.4078. Min Range: -1.4078

Max Act: 1.1484. Min Act: -0.0000

Data Index: 1219990 (The Pile)

Max Activating Token Index: 623

Text #9

Max Range: 1.4078. Min Range: -1.4078

Max Act: 1.0697. Min Act: -0.0000

Data Index: 1811372 (The Pile)

Max Activating Token Index: 456

Text #10

Max Range: 1.4078. Min Range: -1.4078

Max Act: 1.0362. Min Act: -0.0000

Data Index: 1402028 (The Pile)

Max Activating Token Index: 197

Text #11

Max Range: 1.4078. Min Range: -1.4078

Max Act: 1.0857. Min Act: -0.0000

Data Index: 1924084 (The Pile)

Max Activating Token Index: 496

Text #12

Max Range: 1.4078. Min Range: -1.4078

Max Act: 1.0859. Min Act: -0.0000

Data Index: 582044 (The Pile)

Max Activating Token Index: 532

Text #13

Max Range: 1.4078. Min Range: -1.4078

Max Act: 1.0721. Min Act: -0.0000

Data Index: 775403 (The Pile)

Max Activating Token Index: 335

Text #14

Max Range: 1.4078. Min Range: -1.4078

Max Act: 1.1026. Min Act: -0.0000

Data Index: 1926884 (The Pile)

Max Activating Token Index: 443

Text #15

Max Range: 1.4078. Min Range: -1.4078

Max Act: 1.1001. Min Act: -0.0000

Data Index: 292944 (The Pile)

Max Activating Token Index: 339

Text #16

Max Range: 1.4078. Min Range: -1.4078

Max Act: 1.0266. Min Act: -0.0000

Data Index: 833044 (The Pile)

Max Activating Token Index: 405

Text #17

Max Range: 1.4078. Min Range: -1.4078

Max Act: 1.0543. Min Act: -0.0000

Data Index: 599474 (The Pile)

Max Activating Token Index: 349

Text #18

Max Range: 1.4078. Min Range: -1.4078

Max Act: 1.0413. Min Act: -0.0000

Data Index: 240694 (The Pile)

Max Activating Token Index: 388

Text #19

Max Range: 1.4078. Min Range: -1.4078

Max Act: 0.9999. Min Act: -0.0000

Data Index: 1259100 (The Pile)

Max Activating Token Index: 737