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

Dataset: The Pile

Neuron 3721 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6517. Min Range: -0.6517

Max Act: 0.6465. Min Act: 0.0001

Data Index: 1959522 (The Pile)

Max Activating Token Index: 220

Text #1

Max Range: 0.6517. Min Range: -0.6517

Max Act: 0.6324. Min Act: -0.0000

Data Index: 979792 (The Pile)

Max Activating Token Index: 99

Text #2

Max Range: 0.6517. Min Range: -0.6517

Max Act: 0.6517. Min Act: 0.0000

Data Index: 8918 (The Pile)

Max Activating Token Index: 215

Text #3

Max Range: 0.6517. Min Range: -0.6517

Max Act: 0.5945. Min Act: -0.0000

Data Index: 1025641 (The Pile)

Max Activating Token Index: 777

Text #4

Max Range: 0.6517. Min Range: -0.6517

Max Act: 0.5444. Min Act: 0.0000

Data Index: 1278048 (The Pile)

Max Activating Token Index: 555

Text #5

Max Range: 0.6517. Min Range: -0.6517

Max Act: 0.5570. Min Act: 0.0000

Data Index: 237178 (The Pile)

Max Activating Token Index: 281

Text #6

Max Range: 0.6517. Min Range: -0.6517

Max Act: 0.5524. Min Act: -0.0000

Data Index: 952493 (The Pile)

Max Activating Token Index: 448

Text #7

Max Range: 0.6517. Min Range: -0.6517

Max Act: 0.5294. Min Act: 0.0000

Data Index: 660598 (The Pile)

Max Activating Token Index: 988

Text #8

Max Range: 0.6517. Min Range: -0.6517

Max Act: 0.5351. Min Act: -0.0000

Data Index: 1567051 (The Pile)

Max Activating Token Index: 320

Text #9

Max Range: 0.6517. Min Range: -0.6517

Max Act: 0.5262. Min Act: -0.0000

Data Index: 1142785 (The Pile)

Max Activating Token Index: 225

Text #10

Max Range: 0.6517. Min Range: -0.6517

Max Act: 0.5560. Min Act: 0.0000

Data Index: 1613874 (The Pile)

Max Activating Token Index: 568

Text #11

Max Range: 0.6517. Min Range: -0.6517

Max Act: 0.5032. Min Act: 0.0000

Data Index: 105761 (The Pile)

Max Activating Token Index: 497

Text #12

Max Range: 0.6517. Min Range: -0.6517

Max Act: 0.5228. Min Act: -0.0000

Data Index: 1673288 (The Pile)

Max Activating Token Index: 264

Text #13

Max Range: 0.6517. Min Range: -0.6517

Max Act: 0.5020. Min Act: 0.0001

Data Index: 1148385 (The Pile)

Max Activating Token Index: 975

Text #14

Max Range: 0.6517. Min Range: -0.6517

Max Act: 0.5198. Min Act: 0.0000

Data Index: 865973 (The Pile)

Max Activating Token Index: 488

Text #15

Max Range: 0.6517. Min Range: -0.6517

Max Act: 0.5148. Min Act: -0.0000

Data Index: 730518 (The Pile)

Max Activating Token Index: 792

Text #16

Max Range: 0.6517. Min Range: -0.6517

Max Act: 0.4805. Min Act: 0.0000

Data Index: 225885 (The Pile)

Max Activating Token Index: 512

Text #17

Max Range: 0.6517. Min Range: -0.6517

Max Act: 0.4553. Min Act: 0.0000

Data Index: 357768 (The Pile)

Max Activating Token Index: 853

Text #18

Max Range: 0.6517. Min Range: -0.6517

Max Act: 0.5384. Min Act: -0.0000

Data Index: 1469634 (The Pile)

Max Activating Token Index: 814

Text #19

Max Range: 0.6517. Min Range: -0.6517

Max Act: 0.5003. Min Act: 0.0000

Data Index: 1946980 (The Pile)

Max Activating Token Index: 45