Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 620 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.6615. Min Act: -0.0000

Data Index: 183510 (The Pile)

Max Activating Token Index: 22

Text #1

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.6681. Min Act: -0.0000

Data Index: 1794172 (The Pile)

Max Activating Token Index: 754

Text #2

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.6314. Min Act: -0.0000

Data Index: 213357 (The Pile)

Max Activating Token Index: 228

Text #3

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.6206. Min Act: -0.0000

Data Index: 788643 (The Pile)

Max Activating Token Index: 761

Text #4

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.5799. Min Act: -0.0000

Data Index: 901869 (The Pile)

Max Activating Token Index: 973

Text #5

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.5826. Min Act: -0.0000

Data Index: 651223 (The Pile)

Max Activating Token Index: 820

Text #6

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.5352. Min Act: -0.0000

Data Index: 609529 (The Pile)

Max Activating Token Index: 150

Text #7

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.5381. Min Act: -0.0000

Data Index: 470328 (The Pile)

Max Activating Token Index: 112

Text #8

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.5163. Min Act: -0.0000

Data Index: 617108 (The Pile)

Max Activating Token Index: 640

Text #9

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.5282. Min Act: -0.0000

Data Index: 1687073 (The Pile)

Max Activating Token Index: 470

Text #10

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.5152. Min Act: -0.0000

Data Index: 1063452 (The Pile)

Max Activating Token Index: 924

Text #11

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.5141. Min Act: -0.0000

Data Index: 1439010 (The Pile)

Max Activating Token Index: 473

Text #12

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.5135. Min Act: -0.0000

Data Index: 1884048 (The Pile)

Max Activating Token Index: 491

Text #13

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.4807. Min Act: -0.0000

Data Index: 898732 (The Pile)

Max Activating Token Index: 768

Text #14

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.5206. Min Act: -0.0000

Data Index: 873337 (The Pile)

Max Activating Token Index: 440

Text #15

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.4939. Min Act: -0.0000

Data Index: 510914 (The Pile)

Max Activating Token Index: 494

Text #16

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.5045. Min Act: -0.0000

Data Index: 1464356 (The Pile)

Max Activating Token Index: 307

Text #17

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.5023. Min Act: -0.0000

Data Index: 1758582 (The Pile)

Max Activating Token Index: 1017

Text #18

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.4756. Min Act: -0.0000

Data Index: 709641 (The Pile)

Max Activating Token Index: 338

Text #19

Max Range: 0.6681. Min Range: -0.6681

Max Act: 0.4770. Min Act: -0.0000

Data Index: 947996 (The Pile)

Max Activating Token Index: 159