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

Dataset: The Pile

Neuron 4441 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.2511. Min Act: -0.0000

Data Index: 943168 (The Pile)

Max Activating Token Index: 469

Text #1

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.2243. Min Act: -0.0000

Data Index: 736021 (The Pile)

Max Activating Token Index: 692

Text #2

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.2336. Min Act: -0.0000

Data Index: 642890 (The Pile)

Max Activating Token Index: 455

Text #3

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.2195. Min Act: -0.0000

Data Index: 1217865 (The Pile)

Max Activating Token Index: 919

Text #4

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.2022. Min Act: -0.0000

Data Index: 524263 (The Pile)

Max Activating Token Index: 192

Text #5

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.2092. Min Act: -0.0000

Data Index: 760416 (The Pile)

Max Activating Token Index: 302

Text #6

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.1960. Min Act: -0.0000

Data Index: 720995 (The Pile)

Max Activating Token Index: 1006

Text #7

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.2264. Min Act: -0.0000

Data Index: 396286 (The Pile)

Max Activating Token Index: 733

Text #8

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.2013. Min Act: -0.0000

Data Index: 1858838 (The Pile)

Max Activating Token Index: 354

Text #9

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.1706. Min Act: -0.0000

Data Index: 839009 (The Pile)

Max Activating Token Index: 777

Text #10

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.2024. Min Act: -0.0000

Data Index: 521018 (The Pile)

Max Activating Token Index: 317

Text #11

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.2002. Min Act: -0.0000

Data Index: 1476348 (The Pile)

Max Activating Token Index: 455

Text #12

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.1746. Min Act: -0.0000

Data Index: 483154 (The Pile)

Max Activating Token Index: 526

Text #13

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.1690. Min Act: -0.0000

Data Index: 536242 (The Pile)

Max Activating Token Index: 660

Text #14

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.1798. Min Act: -0.0000

Data Index: 1080725 (The Pile)

Max Activating Token Index: 473

Text #15

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.1846. Min Act: -0.0000

Data Index: 294242 (The Pile)

Max Activating Token Index: 80

Text #16

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.2044. Min Act: -0.0000

Data Index: 18305 (The Pile)

Max Activating Token Index: 626

Text #17

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.1721. Min Act: -0.0000

Data Index: 1581967 (The Pile)

Max Activating Token Index: 986

Text #18

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.1547. Min Act: -0.0000

Data Index: 1073688 (The Pile)

Max Activating Token Index: 979

Text #19

Max Range: 0.2511. Min Range: -0.2511

Max Act: 0.1669. Min Act: -0.0000

Data Index: 1687474 (The Pile)

Max Activating Token Index: 232