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

Dataset: The Pile

Neuron 4674 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.7409. Min Act: -0.0000

Data Index: 464019 (The Pile)

Max Activating Token Index: 415

Text #1

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.7829. Min Act: -0.0000

Data Index: 244510 (The Pile)

Max Activating Token Index: 295

Text #2

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.6811. Min Act: -0.0000

Data Index: 824261 (The Pile)

Max Activating Token Index: 552

Text #3

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.6853. Min Act: -0.0000

Data Index: 1327363 (The Pile)

Max Activating Token Index: 823

Text #4

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.7389. Min Act: -0.0000

Data Index: 922264 (The Pile)

Max Activating Token Index: 322

Text #5

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.7004. Min Act: -0.0000

Data Index: 1119161 (The Pile)

Max Activating Token Index: 410

Text #6

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.6920. Min Act: -0.0000

Data Index: 1115807 (The Pile)

Max Activating Token Index: 468

Text #7

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.6245. Min Act: -0.0000

Data Index: 1076415 (The Pile)

Max Activating Token Index: 520

Text #8

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.7113. Min Act: -0.0000

Data Index: 1037499 (The Pile)

Max Activating Token Index: 74

Text #9

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.6996. Min Act: -0.0000

Data Index: 575997 (The Pile)

Max Activating Token Index: 179

Text #10

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.6549. Min Act: -0.0000

Data Index: 496852 (The Pile)

Max Activating Token Index: 227

Text #11

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.6742. Min Act: -0.0000

Data Index: 656225 (The Pile)

Max Activating Token Index: 204

Text #12

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.6726. Min Act: -0.0000

Data Index: 918225 (The Pile)

Max Activating Token Index: 590

Text #13

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.6732. Min Act: -0.0000

Data Index: 1799575 (The Pile)

Max Activating Token Index: 370

Text #14

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.6666. Min Act: -0.0000

Data Index: 779423 (The Pile)

Max Activating Token Index: 382

Text #15

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.6389. Min Act: -0.0000

Data Index: 320013 (The Pile)

Max Activating Token Index: 639

Text #16

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.5923. Min Act: -0.0000

Data Index: 95403 (The Pile)

Max Activating Token Index: 606

Text #17

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.6434. Min Act: -0.0000

Data Index: 468959 (The Pile)

Max Activating Token Index: 251

Text #18

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.6426. Min Act: -0.0000

Data Index: 40433 (The Pile)

Max Activating Token Index: 491

Text #19

Max Range: 0.7829. Min Range: -0.7829

Max Act: 0.6377. Min Act: -0.0000

Data Index: 684477 (The Pile)

Max Activating Token Index: 330