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

Dataset: The Pile

Neuron 950 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.2320. Min Range: -1.2320

Max Act: 1.1992. Min Act: -0.0000

Data Index: 840701 (The Pile)

Max Activating Token Index: 598

Text #1

Max Range: 1.2320. Min Range: -1.2320

Max Act: 1.2320. Min Act: -0.0000

Data Index: 1118817 (The Pile)

Max Activating Token Index: 583

Text #2

Max Range: 1.2320. Min Range: -1.2320

Max Act: 1.0966. Min Act: -0.0000

Data Index: 991529 (The Pile)

Max Activating Token Index: 607

Text #3

Max Range: 1.2320. Min Range: -1.2320

Max Act: 1.0920. Min Act: -0.0000

Data Index: 174920 (The Pile)

Max Activating Token Index: 442

Text #4

Max Range: 1.2320. Min Range: -1.2320

Max Act: 0.9798. Min Act: -0.0000

Data Index: 1863139 (The Pile)

Max Activating Token Index: 433

Text #5

Max Range: 1.2320. Min Range: -1.2320

Max Act: 0.9306. Min Act: -0.0000

Data Index: 141953 (The Pile)

Max Activating Token Index: 874

Text #6

Max Range: 1.2320. Min Range: -1.2320

Max Act: 0.9778. Min Act: -0.0000

Data Index: 1056939 (The Pile)

Max Activating Token Index: 555

Text #7

Max Range: 1.2320. Min Range: -1.2320

Max Act: 0.9632. Min Act: -0.0000

Data Index: 1233592 (The Pile)

Max Activating Token Index: 301

Text #8

Max Range: 1.2320. Min Range: -1.2320

Max Act: 0.8948. Min Act: -0.0000

Data Index: 476384 (The Pile)

Max Activating Token Index: 482

Text #9

Max Range: 1.2320. Min Range: -1.2320

Max Act: 0.9442. Min Act: -0.0000

Data Index: 287087 (The Pile)

Max Activating Token Index: 457

Text #10

Max Range: 1.2320. Min Range: -1.2320

Max Act: 0.9486. Min Act: -0.0000

Data Index: 385664 (The Pile)

Max Activating Token Index: 375

Text #11

Max Range: 1.2320. Min Range: -1.2320

Max Act: 0.9349. Min Act: -0.0000

Data Index: 1824022 (The Pile)

Max Activating Token Index: 634

Text #12

Max Range: 1.2320. Min Range: -1.2320

Max Act: 0.9095. Min Act: -0.0000

Data Index: 505996 (The Pile)

Max Activating Token Index: 923

Text #13

Max Range: 1.2320. Min Range: -1.2320

Max Act: 0.9822. Min Act: -0.0000

Data Index: 91567 (The Pile)

Max Activating Token Index: 801

Text #14

Max Range: 1.2320. Min Range: -1.2320

Max Act: 0.9841. Min Act: 0.0000

Data Index: 470924 (The Pile)

Max Activating Token Index: 396

Text #15

Max Range: 1.2320. Min Range: -1.2320

Max Act: 0.9270. Min Act: -0.0000

Data Index: 360076 (The Pile)

Max Activating Token Index: 300

Text #16

Max Range: 1.2320. Min Range: -1.2320

Max Act: 0.8860. Min Act: 0.0000

Data Index: 1819939 (The Pile)

Max Activating Token Index: 223

Text #17

Max Range: 1.2320. Min Range: -1.2320

Max Act: 0.9491. Min Act: 0.0000

Data Index: 597555 (The Pile)

Max Activating Token Index: 160

Text #18

Max Range: 1.2320. Min Range: -1.2320

Max Act: 0.9599. Min Act: -0.0000

Data Index: 22556 (The Pile)

Max Activating Token Index: 565

Text #19

Max Range: 1.2320. Min Range: -1.2320

Max Act: 0.8384. Min Act: -0.0000

Data Index: 504952 (The Pile)

Max Activating Token Index: 816