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

Dataset: The Pile

Neuron 1537 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: 0.8303. Min Range: -0.8303

Max Act: 0.8303. Min Act: -0.0000

Data Index: 396950 (The Pile)

Max Activating Token Index: 449

Text #1

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.6365. Min Act: -0.0000

Data Index: 643066 (The Pile)

Max Activating Token Index: 543

Text #2

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.6454. Min Act: -0.0000

Data Index: 575416 (The Pile)

Max Activating Token Index: 798

Text #3

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.6663. Min Act: -0.0000

Data Index: 1678168 (The Pile)

Max Activating Token Index: 722

Text #4

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.6120. Min Act: -0.0000

Data Index: 166342 (The Pile)

Max Activating Token Index: 538

Text #5

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.6258. Min Act: -0.0000

Data Index: 872220 (The Pile)

Max Activating Token Index: 644

Text #6

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.5133. Min Act: -0.0000

Data Index: 640732 (The Pile)

Max Activating Token Index: 193

Text #7

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.4787. Min Act: -0.0000

Data Index: 1056117 (The Pile)

Max Activating Token Index: 953

Text #8

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.5329. Min Act: -0.0000

Data Index: 1103824 (The Pile)

Max Activating Token Index: 626

Text #9

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.6174. Min Act: -0.0000

Data Index: 1715088 (The Pile)

Max Activating Token Index: 941

Text #10

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.5162. Min Act: -0.0000

Data Index: 998839 (The Pile)

Max Activating Token Index: 935

Text #11

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.5734. Min Act: -0.0000

Data Index: 511683 (The Pile)

Max Activating Token Index: 498

Text #12

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.5975. Min Act: -0.0000

Data Index: 131836 (The Pile)

Max Activating Token Index: 817

Text #13

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.5534. Min Act: -0.0000

Data Index: 746290 (The Pile)

Max Activating Token Index: 577

Text #14

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.5549. Min Act: -0.0000

Data Index: 428672 (The Pile)

Max Activating Token Index: 598

Text #15

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.5414. Min Act: -0.0000

Data Index: 993859 (The Pile)

Max Activating Token Index: 746

Text #16

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.5567. Min Act: -0.0000

Data Index: 1439017 (The Pile)

Max Activating Token Index: 508

Text #17

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.5743. Min Act: -0.0000

Data Index: 973394 (The Pile)

Max Activating Token Index: 222

Text #18

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.5523. Min Act: -0.0000

Data Index: 152183 (The Pile)

Max Activating Token Index: 932

Text #19

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.5461. Min Act: -0.0000

Data Index: 1804313 (The Pile)

Max Activating Token Index: 34