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

Dataset: The Pile

Neuron 4149 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: 1.3671. Min Range: -1.3671

Max Act: 1.3650. Min Act: -0.0000

Data Index: 1870078 (The Pile)

Max Activating Token Index: 1001

Text #1

Max Range: 1.3671. Min Range: -1.3671

Max Act: 1.3074. Min Act: -0.0000

Data Index: 471693 (The Pile)

Max Activating Token Index: 843

Text #2

Max Range: 1.3671. Min Range: -1.3671

Max Act: 1.3325. Min Act: -0.0000

Data Index: 1422228 (The Pile)

Max Activating Token Index: 983

Text #3

Max Range: 1.3671. Min Range: -1.3671

Max Act: 1.3671. Min Act: -0.0000

Data Index: 123884 (The Pile)

Max Activating Token Index: 917

Text #4

Max Range: 1.3671. Min Range: -1.3671

Max Act: 1.3128. Min Act: -0.0000

Data Index: 538495 (The Pile)

Max Activating Token Index: 27

Text #5

Max Range: 1.3671. Min Range: -1.3671

Max Act: 1.3010. Min Act: -0.0000

Data Index: 1070727 (The Pile)

Max Activating Token Index: 541

Text #6

Max Range: 1.3671. Min Range: -1.3671

Max Act: 1.3279. Min Act: -0.0000

Data Index: 24533 (The Pile)

Max Activating Token Index: 87

Text #7

Max Range: 1.3671. Min Range: -1.3671

Max Act: 1.2554. Min Act: -0.0000

Data Index: 1405573 (The Pile)

Max Activating Token Index: 676

Text #8

Max Range: 1.3671. Min Range: -1.3671

Max Act: 1.2455. Min Act: -0.0000

Data Index: 148395 (The Pile)

Max Activating Token Index: 26

Text #9

Max Range: 1.3671. Min Range: -1.3671

Max Act: 1.2684. Min Act: -0.0000

Data Index: 1610263 (The Pile)

Max Activating Token Index: 15

Text #10

Max Range: 1.3671. Min Range: -1.3671

Max Act: 1.2518. Min Act: -0.0000

Data Index: 1364512 (The Pile)

Max Activating Token Index: 103

Text #11

Max Range: 1.3671. Min Range: -1.3671

Max Act: 1.2498. Min Act: -0.0000

Data Index: 480687 (The Pile)

Max Activating Token Index: 807

Text #12

Max Range: 1.3671. Min Range: -1.3671

Max Act: 1.2489. Min Act: -0.0000

Data Index: 661949 (The Pile)

Max Activating Token Index: 690

Text #13

Max Range: 1.3671. Min Range: -1.3671

Max Act: 1.2795. Min Act: -0.0000

Data Index: 471524 (The Pile)

Max Activating Token Index: 262

Text #14

Max Range: 1.3671. Min Range: -1.3671

Max Act: 1.2690. Min Act: -0.0000

Data Index: 1013532 (The Pile)

Max Activating Token Index: 585

Text #15

Max Range: 1.3671. Min Range: -1.3671

Max Act: 1.1529. Min Act: -0.0000

Data Index: 1296369 (The Pile)

Max Activating Token Index: 937

Text #16

Max Range: 1.3671. Min Range: -1.3671

Max Act: 1.1847. Min Act: -0.0000

Data Index: 564510 (The Pile)

Max Activating Token Index: 928

Text #17

Max Range: 1.3671. Min Range: -1.3671

Max Act: 1.1412. Min Act: -0.0000

Data Index: 1886082 (The Pile)

Max Activating Token Index: 507

Text #18

Max Range: 1.3671. Min Range: -1.3671

Max Act: 1.2112. Min Act: -0.0000

Data Index: 1557875 (The Pile)

Max Activating Token Index: 871

Text #19

Max Range: 1.3671. Min Range: -1.3671

Max Act: 1.2060. Min Act: -0.0000

Data Index: 696338 (The Pile)

Max Activating Token Index: 335