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

Dataset: The Pile

Neuron 4252 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: 8.3356. Min Range: -8.3356

Max Act: 8.2406. Min Act: -0.0000

Data Index: 1091434 (The Pile)

Max Activating Token Index: 385

Text #1

Max Range: 8.3356. Min Range: -8.3356

Max Act: 8.3356. Min Act: -0.0000

Data Index: 1157400 (The Pile)

Max Activating Token Index: 723

Text #2

Max Range: 8.3356. Min Range: -8.3356

Max Act: 8.1232. Min Act: -0.0000

Data Index: 302255 (The Pile)

Max Activating Token Index: 696

Text #3

Max Range: 8.3356. Min Range: -8.3356

Max Act: 7.8976. Min Act: -0.0000

Data Index: 454206 (The Pile)

Max Activating Token Index: 620

Text #4

Max Range: 8.3356. Min Range: -8.3356

Max Act: 8.1986. Min Act: -0.0000

Data Index: 1882881 (The Pile)

Max Activating Token Index: 332

Text #5

Max Range: 8.3356. Min Range: -8.3356

Max Act: 7.1342. Min Act: -0.0000

Data Index: 1362575 (The Pile)

Max Activating Token Index: 849

Text #6

Max Range: 8.3356. Min Range: -8.3356

Max Act: 7.7318. Min Act: -0.0000

Data Index: 660723 (The Pile)

Max Activating Token Index: 428

Text #7

Max Range: 8.3356. Min Range: -8.3356

Max Act: 7.6518. Min Act: -0.0000

Data Index: 1272021 (The Pile)

Max Activating Token Index: 507

Text #8

Max Range: 8.3356. Min Range: -8.3356

Max Act: 7.8695. Min Act: -0.0000

Data Index: 1461001 (The Pile)

Max Activating Token Index: 549

Text #9

Max Range: 8.3356. Min Range: -8.3356

Max Act: 7.9331. Min Act: -0.0000

Data Index: 13689 (The Pile)

Max Activating Token Index: 266

Text #10

Max Range: 8.3356. Min Range: -8.3356

Max Act: 7.7797. Min Act: -0.0000

Data Index: 1032646 (The Pile)

Max Activating Token Index: 183

Text #11

Max Range: 8.3356. Min Range: -8.3356

Max Act: 7.4626. Min Act: -0.0000

Data Index: 123662 (The Pile)

Max Activating Token Index: 466

Text #12

Max Range: 8.3356. Min Range: -8.3356

Max Act: 7.5836. Min Act: -0.0000

Data Index: 138600 (The Pile)

Max Activating Token Index: 241

Text #13

Max Range: 8.3356. Min Range: -8.3356

Max Act: 7.2671. Min Act: -0.0000

Data Index: 1588131 (The Pile)

Max Activating Token Index: 352

Text #14

Max Range: 8.3356. Min Range: -8.3356

Max Act: 7.7780. Min Act: -0.0000

Data Index: 1473389 (The Pile)

Max Activating Token Index: 784

Text #15

Max Range: 8.3356. Min Range: -8.3356

Max Act: 7.4378. Min Act: -0.0000

Data Index: 1745252 (The Pile)

Max Activating Token Index: 96

Text #16

Max Range: 8.3356. Min Range: -8.3356

Max Act: 6.7729. Min Act: -0.0000

Data Index: 1209211 (The Pile)

Max Activating Token Index: 770

Text #17

Max Range: 8.3356. Min Range: -8.3356

Max Act: 7.0274. Min Act: -0.0000

Data Index: 1013518 (The Pile)

Max Activating Token Index: 714

Text #18

Max Range: 8.3356. Min Range: -8.3356

Max Act: 6.9771. Min Act: -0.0000

Data Index: 1323907 (The Pile)

Max Activating Token Index: 791

Text #19

Max Range: 8.3356. Min Range: -8.3356

Max Act: 7.7958. Min Act: -0.0000

Data Index: 1206528 (The Pile)

Max Activating Token Index: 829