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

Dataset: The Pile

Neuron 1110 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: 1.5575. Min Range: -1.5575

Max Act: 1.4919. Min Act: -0.0000

Data Index: 939860 (The Pile)

Max Activating Token Index: 578

Text #1

Max Range: 1.5575. Min Range: -1.5575

Max Act: 1.5575. Min Act: 0.0000

Data Index: 408815 (The Pile)

Max Activating Token Index: 185

Text #2

Max Range: 1.5575. Min Range: -1.5575

Max Act: 1.3983. Min Act: -0.0000

Data Index: 1303249 (The Pile)

Max Activating Token Index: 181

Text #3

Max Range: 1.5575. Min Range: -1.5575

Max Act: 1.2526. Min Act: -0.0000

Data Index: 1413966 (The Pile)

Max Activating Token Index: 944

Text #4

Max Range: 1.5575. Min Range: -1.5575

Max Act: 1.2855. Min Act: -0.0000

Data Index: 1100234 (The Pile)

Max Activating Token Index: 846

Text #5

Max Range: 1.5575. Min Range: -1.5575

Max Act: 1.3126. Min Act: -0.0000

Data Index: 714101 (The Pile)

Max Activating Token Index: 284

Text #6

Max Range: 1.5575. Min Range: -1.5575

Max Act: 1.2307. Min Act: 0.0000

Data Index: 953780 (The Pile)

Max Activating Token Index: 798

Text #7

Max Range: 1.5575. Min Range: -1.5575

Max Act: 1.3039. Min Act: -0.0000

Data Index: 642734 (The Pile)

Max Activating Token Index: 134

Text #8

Max Range: 1.5575. Min Range: -1.5575

Max Act: 1.3038. Min Act: -0.0000

Data Index: 1154603 (The Pile)

Max Activating Token Index: 396

Text #9

Max Range: 1.5575. Min Range: -1.5575

Max Act: 1.2264. Min Act: -0.0000

Data Index: 1610364 (The Pile)

Max Activating Token Index: 650

Text #10

Max Range: 1.5575. Min Range: -1.5575

Max Act: 1.2621. Min Act: -0.0000

Data Index: 261289 (The Pile)

Max Activating Token Index: 151

Text #11

Max Range: 1.5575. Min Range: -1.5575

Max Act: 1.1310. Min Act: -0.0000

Data Index: 1034578 (The Pile)

Max Activating Token Index: 321

Text #12

Max Range: 1.5575. Min Range: -1.5575

Max Act: 1.2325. Min Act: -0.0000

Data Index: 1153207 (The Pile)

Max Activating Token Index: 569

Text #13

Max Range: 1.5575. Min Range: -1.5575

Max Act: 1.1505. Min Act: -0.0000

Data Index: 252867 (The Pile)

Max Activating Token Index: 1011

Text #14

Max Range: 1.5575. Min Range: -1.5575

Max Act: 1.1854. Min Act: -0.0000

Data Index: 399869 (The Pile)

Max Activating Token Index: 528

Text #15

Max Range: 1.5575. Min Range: -1.5575

Max Act: 1.2038. Min Act: -0.0000

Data Index: 1718010 (The Pile)

Max Activating Token Index: 522

Text #16

Max Range: 1.5575. Min Range: -1.5575

Max Act: 1.1715. Min Act: -0.0000

Data Index: 1421118 (The Pile)

Max Activating Token Index: 932

Text #17

Max Range: 1.5575. Min Range: -1.5575

Max Act: 1.1571. Min Act: -0.0000

Data Index: 1464594 (The Pile)

Max Activating Token Index: 468

Text #18

Max Range: 1.5575. Min Range: -1.5575

Max Act: 1.2731. Min Act: -0.0000

Data Index: 124848 (The Pile)

Max Activating Token Index: 594

Text #19

Max Range: 1.5575. Min Range: -1.5575

Max Act: 1.1773. Min Act: -0.0000

Data Index: 153721 (The Pile)

Max Activating Token Index: 933