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

Dataset: The Pile

Neuron 3862 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: 1.4629. Min Range: -1.4629

Max Act: 1.4629. Min Act: -0.0000

Data Index: 1917637 (The Pile)

Max Activating Token Index: 930

Text #1

Max Range: 1.4629. Min Range: -1.4629

Max Act: 1.3146. Min Act: -0.0000

Data Index: 1400050 (The Pile)

Max Activating Token Index: 704

Text #2

Max Range: 1.4629. Min Range: -1.4629

Max Act: 1.3297. Min Act: -0.0000

Data Index: 519418 (The Pile)

Max Activating Token Index: 774

Text #3

Max Range: 1.4629. Min Range: -1.4629

Max Act: 1.3139. Min Act: -0.0000

Data Index: 1364161 (The Pile)

Max Activating Token Index: 395

Text #4

Max Range: 1.4629. Min Range: -1.4629

Max Act: 1.2368. Min Act: -0.0000

Data Index: 74531 (The Pile)

Max Activating Token Index: 479

Text #5

Max Range: 1.4629. Min Range: -1.4629

Max Act: 1.1360. Min Act: -0.0000

Data Index: 1515514 (The Pile)

Max Activating Token Index: 464

Text #6

Max Range: 1.4629. Min Range: -1.4629

Max Act: 1.1141. Min Act: -0.0000

Data Index: 579833 (The Pile)

Max Activating Token Index: 458

Text #7

Max Range: 1.4629. Min Range: -1.4629

Max Act: 1.0695. Min Act: -0.0000

Data Index: 1636452 (The Pile)

Max Activating Token Index: 287

Text #8

Max Range: 1.4629. Min Range: -1.4629

Max Act: 1.1292. Min Act: -0.0000

Data Index: 1562470 (The Pile)

Max Activating Token Index: 773

Text #9

Max Range: 1.4629. Min Range: -1.4629

Max Act: 0.9397. Min Act: -0.0000

Data Index: 647359 (The Pile)

Max Activating Token Index: 773

Text #10

Max Range: 1.4629. Min Range: -1.4629

Max Act: 1.0560. Min Act: -0.0000

Data Index: 1449491 (The Pile)

Max Activating Token Index: 902

Text #11

Max Range: 1.4629. Min Range: -1.4629

Max Act: 1.0503. Min Act: -0.0000

Data Index: 272513 (The Pile)

Max Activating Token Index: 789

Text #12

Max Range: 1.4629. Min Range: -1.4629

Max Act: 1.0235. Min Act: -0.0000

Data Index: 242272 (The Pile)

Max Activating Token Index: 817

Text #13

Max Range: 1.4629. Min Range: -1.4629

Max Act: 1.0315. Min Act: -0.0000

Data Index: 1505187 (The Pile)

Max Activating Token Index: 254

Text #14

Max Range: 1.4629. Min Range: -1.4629

Max Act: 0.8883. Min Act: -0.0000

Data Index: 1146064 (The Pile)

Max Activating Token Index: 289

Text #15

Max Range: 1.4629. Min Range: -1.4629

Max Act: 0.9010. Min Act: -0.0000

Data Index: 669184 (The Pile)

Max Activating Token Index: 439

Text #16

Max Range: 1.4629. Min Range: -1.4629

Max Act: 0.8867. Min Act: -0.0000

Data Index: 454805 (The Pile)

Max Activating Token Index: 793

Text #17

Max Range: 1.4629. Min Range: -1.4629

Max Act: 0.9433. Min Act: -0.0000

Data Index: 1615126 (The Pile)

Max Activating Token Index: 473

Text #18

Max Range: 1.4629. Min Range: -1.4629

Max Act: 0.8623. Min Act: -0.0000

Data Index: 351871 (The Pile)

Max Activating Token Index: 654

Text #19

Max Range: 1.4629. Min Range: -1.4629

Max Act: 1.0104. Min Act: -0.0000

Data Index: 779315 (The Pile)

Max Activating Token Index: 699