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

Dataset: The Pile

Neuron 4457 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: 0.7236. Min Range: -0.7236

Max Act: 0.7236. Min Act: -0.0000

Data Index: 1578130 (The Pile)

Max Activating Token Index: 23

Text #1

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.6761. Min Act: -0.0000

Data Index: 915449 (The Pile)

Max Activating Token Index: 734

Text #2

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.6029. Min Act: -0.0000

Data Index: 1500479 (The Pile)

Max Activating Token Index: 405

Text #3

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.5913. Min Act: -0.0000

Data Index: 18432 (The Pile)

Max Activating Token Index: 101

Text #4

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.5902. Min Act: -0.0000

Data Index: 1025750 (The Pile)

Max Activating Token Index: 508

Text #5

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.5582. Min Act: -0.0000

Data Index: 1553618 (The Pile)

Max Activating Token Index: 433

Text #6

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.6040. Min Act: -0.0000

Data Index: 1277483 (The Pile)

Max Activating Token Index: 58

Text #7

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.5436. Min Act: -0.0000

Data Index: 196012 (The Pile)

Max Activating Token Index: 357

Text #8

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.5403. Min Act: -0.0000

Data Index: 930620 (The Pile)

Max Activating Token Index: 29

Text #9

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.5684. Min Act: -0.0000

Data Index: 732378 (The Pile)

Max Activating Token Index: 350

Text #10

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.4967. Min Act: -0.0000

Data Index: 357396 (The Pile)

Max Activating Token Index: 118

Text #11

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.5789. Min Act: -0.0000

Data Index: 1899940 (The Pile)

Max Activating Token Index: 660

Text #12

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.5251. Min Act: -0.0000

Data Index: 1739827 (The Pile)

Max Activating Token Index: 38

Text #13

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.5399. Min Act: -0.0000

Data Index: 1963020 (The Pile)

Max Activating Token Index: 773

Text #14

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.5406. Min Act: -0.0000

Data Index: 412976 (The Pile)

Max Activating Token Index: 17

Text #15

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.5050. Min Act: -0.0000

Data Index: 1010682 (The Pile)

Max Activating Token Index: 681

Text #16

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.5040. Min Act: -0.0000

Data Index: 1311425 (The Pile)

Max Activating Token Index: 859

Text #17

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.5253. Min Act: -0.0000

Data Index: 670646 (The Pile)

Max Activating Token Index: 62

Text #18

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.5205. Min Act: -0.0000

Data Index: 594664 (The Pile)

Max Activating Token Index: 29

Text #19

Max Range: 0.7236. Min Range: -0.7236

Max Act: 0.4740. Min Act: -0.0000

Data Index: 1738834 (The Pile)

Max Activating Token Index: 469