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

Dataset: The Pile

Neuron 3157 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.5061. Min Act: -0.0000

Data Index: 1642815 (The Pile)

Max Activating Token Index: 360

Text #1

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.4660. Min Act: -0.0000

Data Index: 988713 (The Pile)

Max Activating Token Index: 867

Text #2

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.4431. Min Act: -0.0000

Data Index: 1518899 (The Pile)

Max Activating Token Index: 683

Text #3

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.3503. Min Act: -0.0000

Data Index: 1516094 (The Pile)

Max Activating Token Index: 661

Text #4

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.2889. Min Act: -0.0000

Data Index: 930219 (The Pile)

Max Activating Token Index: 519

Text #5

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.2437. Min Act: -0.0000

Data Index: 1875465 (The Pile)

Max Activating Token Index: 33

Text #6

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.3620. Min Act: -0.0000

Data Index: 980735 (The Pile)

Max Activating Token Index: 621

Text #7

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.2018. Min Act: -0.0000

Data Index: 1283672 (The Pile)

Max Activating Token Index: 1020

Text #8

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.4275. Min Act: -0.0000

Data Index: 1673164 (The Pile)

Max Activating Token Index: 937

Text #9

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.2446. Min Act: -0.0000

Data Index: 710665 (The Pile)

Max Activating Token Index: 675

Text #10

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.3219. Min Act: -0.0000

Data Index: 201550 (The Pile)

Max Activating Token Index: 733

Text #11

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.2683. Min Act: -0.0000

Data Index: 1574411 (The Pile)

Max Activating Token Index: 1000

Text #12

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.3018. Min Act: -0.0000

Data Index: 652106 (The Pile)

Max Activating Token Index: 618

Text #13

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.2823. Min Act: -0.0000

Data Index: 338767 (The Pile)

Max Activating Token Index: 426

Text #14

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.1349. Min Act: -0.0000

Data Index: 809359 (The Pile)

Max Activating Token Index: 592

Text #15

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.2631. Min Act: -0.0000

Data Index: 666655 (The Pile)

Max Activating Token Index: 915

Text #16

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.2358. Min Act: -0.0000

Data Index: 307052 (The Pile)

Max Activating Token Index: 359

Text #17

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.1983. Min Act: -0.0000

Data Index: 1285722 (The Pile)

Max Activating Token Index: 681

Text #18

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.3407. Min Act: -0.0000

Data Index: 314055 (The Pile)

Max Activating Token Index: 583

Text #19

Max Range: 1.5061. Min Range: -1.5061

Max Act: 1.2305. Min Act: -0.0000

Data Index: 210925 (The Pile)

Max Activating Token Index: 945