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

Dataset: The Pile

Neuron 1459 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: 3.4867. Min Range: -3.4867

Max Act: 3.4396. Min Act: -0.0000

Data Index: 424591 (The Pile)

Max Activating Token Index: 238

Text #1

Max Range: 3.4867. Min Range: -3.4867

Max Act: 2.8430. Min Act: -0.0000

Data Index: 1645207 (The Pile)

Max Activating Token Index: 271

Text #2

Max Range: 3.4867. Min Range: -3.4867

Max Act: 3.3233. Min Act: -0.0000

Data Index: 1646017 (The Pile)

Max Activating Token Index: 570

Text #3

Max Range: 3.4867. Min Range: -3.4867

Max Act: 3.4473. Min Act: -0.0000

Data Index: 762086 (The Pile)

Max Activating Token Index: 209

Text #4

Max Range: 3.4867. Min Range: -3.4867

Max Act: 3.4867. Min Act: -0.0000

Data Index: 690683 (The Pile)

Max Activating Token Index: 439

Text #5

Max Range: 3.4867. Min Range: -3.4867

Max Act: 3.3710. Min Act: -0.0000

Data Index: 1401054 (The Pile)

Max Activating Token Index: 319

Text #6

Max Range: 3.4867. Min Range: -3.4867

Max Act: 3.0460. Min Act: -0.0000

Data Index: 1506117 (The Pile)

Max Activating Token Index: 458

Text #7

Max Range: 3.4867. Min Range: -3.4867

Max Act: 2.8228. Min Act: -0.0000

Data Index: 1832403 (The Pile)

Max Activating Token Index: 733

Text #8

Max Range: 3.4867. Min Range: -3.4867

Max Act: 3.0993. Min Act: -0.0000

Data Index: 160316 (The Pile)

Max Activating Token Index: 762

Text #9

Max Range: 3.4867. Min Range: -3.4867

Max Act: 3.0709. Min Act: -0.0000

Data Index: 1005383 (The Pile)

Max Activating Token Index: 166

Text #10

Max Range: 3.4867. Min Range: -3.4867

Max Act: 2.9490. Min Act: -0.0000

Data Index: 991144 (The Pile)

Max Activating Token Index: 380

Text #11

Max Range: 3.4867. Min Range: -3.4867

Max Act: 2.9478. Min Act: -0.0000

Data Index: 1027603 (The Pile)

Max Activating Token Index: 427

Text #12

Max Range: 3.4867. Min Range: -3.4867

Max Act: 2.5025. Min Act: -0.0000

Data Index: 1054304 (The Pile)

Max Activating Token Index: 639

Text #13

Max Range: 3.4867. Min Range: -3.4867

Max Act: 2.8784. Min Act: -0.0000

Data Index: 1758989 (The Pile)

Max Activating Token Index: 525

Text #14

Max Range: 3.4867. Min Range: -3.4867

Max Act: 2.9447. Min Act: -0.0000

Data Index: 74443 (The Pile)

Max Activating Token Index: 213

Text #15

Max Range: 3.4867. Min Range: -3.4867

Max Act: 2.7228. Min Act: -0.0000

Data Index: 1450684 (The Pile)

Max Activating Token Index: 606

Text #16

Max Range: 3.4867. Min Range: -3.4867

Max Act: 2.5432. Min Act: -0.0000

Data Index: 1807146 (The Pile)

Max Activating Token Index: 858

Text #17

Max Range: 3.4867. Min Range: -3.4867

Max Act: 2.5167. Min Act: -0.0000

Data Index: 630583 (The Pile)

Max Activating Token Index: 355

Text #18

Max Range: 3.4867. Min Range: -3.4867

Max Act: 2.3324. Min Act: -0.0000

Data Index: 392951 (The Pile)

Max Activating Token Index: 687

Text #19

Max Range: 3.4867. Min Range: -3.4867

Max Act: 2.4658. Min Act: -0.0000

Data Index: 579694 (The Pile)

Max Activating Token Index: 267