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

Dataset: The Pile

Neuron 4843 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: 1.7486. Min Range: -1.7486

Max Act: 1.6969. Min Act: -0.0000

Data Index: 1955719 (The Pile)

Max Activating Token Index: 166

Text #1

Max Range: 1.7486. Min Range: -1.7486

Max Act: 1.7486. Min Act: -0.0000

Data Index: 268666 (The Pile)

Max Activating Token Index: 882

Text #2

Max Range: 1.7486. Min Range: -1.7486

Max Act: 1.4726. Min Act: -0.0000

Data Index: 886758 (The Pile)

Max Activating Token Index: 357

Text #3

Max Range: 1.7486. Min Range: -1.7486

Max Act: 1.4004. Min Act: -0.0000

Data Index: 349965 (The Pile)

Max Activating Token Index: 564

Text #4

Max Range: 1.7486. Min Range: -1.7486

Max Act: 1.4434. Min Act: -0.0000

Data Index: 1890494 (The Pile)

Max Activating Token Index: 91

Text #5

Max Range: 1.7486. Min Range: -1.7486

Max Act: 1.4780. Min Act: -0.0000

Data Index: 947781 (The Pile)

Max Activating Token Index: 391

Text #6

Max Range: 1.7486. Min Range: -1.7486

Max Act: 1.4657. Min Act: -0.0000

Data Index: 553840 (The Pile)

Max Activating Token Index: 657

Text #7

Max Range: 1.7486. Min Range: -1.7486

Max Act: 1.6032. Min Act: -0.0000

Data Index: 1477915 (The Pile)

Max Activating Token Index: 219

Text #8

Max Range: 1.7486. Min Range: -1.7486

Max Act: 1.3834. Min Act: -0.0000

Data Index: 226669 (The Pile)

Max Activating Token Index: 917

Text #9

Max Range: 1.7486. Min Range: -1.7486

Max Act: 1.4149. Min Act: -0.0000

Data Index: 1993686 (The Pile)

Max Activating Token Index: 471

Text #10

Max Range: 1.7486. Min Range: -1.7486

Max Act: 1.3238. Min Act: -0.0000

Data Index: 625203 (The Pile)

Max Activating Token Index: 1003

Text #11

Max Range: 1.7486. Min Range: -1.7486

Max Act: 1.4089. Min Act: -0.0000

Data Index: 1467459 (The Pile)

Max Activating Token Index: 646

Text #12

Max Range: 1.7486. Min Range: -1.7486

Max Act: 1.2723. Min Act: -0.0000

Data Index: 1595393 (The Pile)

Max Activating Token Index: 297

Text #13

Max Range: 1.7486. Min Range: -1.7486

Max Act: 1.3507. Min Act: -0.0000

Data Index: 1711790 (The Pile)

Max Activating Token Index: 269

Text #14

Max Range: 1.7486. Min Range: -1.7486

Max Act: 1.3449. Min Act: -0.0000

Data Index: 233886 (The Pile)

Max Activating Token Index: 962

Text #15

Max Range: 1.7486. Min Range: -1.7486

Max Act: 1.3464. Min Act: -0.0000

Data Index: 382579 (The Pile)

Max Activating Token Index: 526

Text #16

Max Range: 1.7486. Min Range: -1.7486

Max Act: 1.3736. Min Act: -0.0000

Data Index: 524446 (The Pile)

Max Activating Token Index: 706

Text #17

Max Range: 1.7486. Min Range: -1.7486

Max Act: 1.4098. Min Act: -0.0000

Data Index: 1179672 (The Pile)

Max Activating Token Index: 395

Text #18

Max Range: 1.7486. Min Range: -1.7486

Max Act: 1.3324. Min Act: -0.0000

Data Index: 1343240 (The Pile)

Max Activating Token Index: 793

Text #19

Max Range: 1.7486. Min Range: -1.7486

Max Act: 1.2906. Min Act: -0.0000

Data Index: 1077531 (The Pile)

Max Activating Token Index: 386