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

Dataset: The Pile

Neuron 3289 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3232. Min Range: -1.3232

Max Act: 1.1417. Min Act: -0.0000

Data Index: 1208210 (The Pile)

Max Activating Token Index: 572

Text #1

Max Range: 1.3232. Min Range: -1.3232

Max Act: 1.3232. Min Act: -0.0000

Data Index: 1603919 (The Pile)

Max Activating Token Index: 576

Text #2

Max Range: 1.3232. Min Range: -1.3232

Max Act: 1.1938. Min Act: -0.0000

Data Index: 1185587 (The Pile)

Max Activating Token Index: 1022

Text #3

Max Range: 1.3232. Min Range: -1.3232

Max Act: 1.1536. Min Act: -0.0000

Data Index: 1193993 (The Pile)

Max Activating Token Index: 1011

Text #4

Max Range: 1.3232. Min Range: -1.3232

Max Act: 1.1321. Min Act: -0.0000

Data Index: 1052686 (The Pile)

Max Activating Token Index: 569

Text #5

Max Range: 1.3232. Min Range: -1.3232

Max Act: 1.1844. Min Act: -0.0000

Data Index: 1909515 (The Pile)

Max Activating Token Index: 748

Text #6

Max Range: 1.3232. Min Range: -1.3232

Max Act: 1.0796. Min Act: -0.0000

Data Index: 617399 (The Pile)

Max Activating Token Index: 113

Text #7

Max Range: 1.3232. Min Range: -1.3232

Max Act: 1.0528. Min Act: -0.0000

Data Index: 1673774 (The Pile)

Max Activating Token Index: 465

Text #8

Max Range: 1.3232. Min Range: -1.3232

Max Act: 1.1107. Min Act: -0.0000

Data Index: 611816 (The Pile)

Max Activating Token Index: 406

Text #9

Max Range: 1.3232. Min Range: -1.3232

Max Act: 0.9646. Min Act: -0.0000

Data Index: 1068595 (The Pile)

Max Activating Token Index: 614

Text #10

Max Range: 1.3232. Min Range: -1.3232

Max Act: 1.1279. Min Act: -0.0000

Data Index: 742249 (The Pile)

Max Activating Token Index: 79

Text #11

Max Range: 1.3232. Min Range: -1.3232

Max Act: 1.1006. Min Act: -0.0000

Data Index: 1670853 (The Pile)

Max Activating Token Index: 236

Text #12

Max Range: 1.3232. Min Range: -1.3232

Max Act: 1.1617. Min Act: -0.0000

Data Index: 1601770 (The Pile)

Max Activating Token Index: 818

Text #13

Max Range: 1.3232. Min Range: -1.3232

Max Act: 1.0638. Min Act: -0.0000

Data Index: 718514 (The Pile)

Max Activating Token Index: 594

Text #14

Max Range: 1.3232. Min Range: -1.3232

Max Act: 1.0598. Min Act: -0.0000

Data Index: 905301 (The Pile)

Max Activating Token Index: 408

Text #15

Max Range: 1.3232. Min Range: -1.3232

Max Act: 1.0712. Min Act: -0.0000

Data Index: 1327564 (The Pile)

Max Activating Token Index: 777

Text #16

Max Range: 1.3232. Min Range: -1.3232

Max Act: 1.0444. Min Act: -0.0000

Data Index: 918423 (The Pile)

Max Activating Token Index: 366

Text #17

Max Range: 1.3232. Min Range: -1.3232

Max Act: 1.1335. Min Act: -0.0000

Data Index: 4539 (The Pile)

Max Activating Token Index: 611

Text #18

Max Range: 1.3232. Min Range: -1.3232

Max Act: 0.9381. Min Act: -0.0000

Data Index: 1479698 (The Pile)

Max Activating Token Index: 554

Text #19

Max Range: 1.3232. Min Range: -1.3232

Max Act: 1.0333. Min Act: -0.0000

Data Index: 351486 (The Pile)

Max Activating Token Index: 728