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

Dataset: The Pile

Neuron 3594 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: 0.8341. Min Range: -0.8341

Max Act: 0.8341. Min Act: -0.0000

Data Index: 1220376 (The Pile)

Max Activating Token Index: 643

Text #1

Max Range: 0.8341. Min Range: -0.8341

Max Act: 0.7831. Min Act: -0.0000

Data Index: 264247 (The Pile)

Max Activating Token Index: 619

Text #2

Max Range: 0.8341. Min Range: -0.8341

Max Act: 0.7649. Min Act: -0.0000

Data Index: 86799 (The Pile)

Max Activating Token Index: 821

Text #3

Max Range: 0.8341. Min Range: -0.8341

Max Act: 0.7883. Min Act: -0.0000

Data Index: 726361 (The Pile)

Max Activating Token Index: 856

Text #4

Max Range: 0.8341. Min Range: -0.8341

Max Act: 0.6145. Min Act: -0.0000

Data Index: 463065 (The Pile)

Max Activating Token Index: 96

Text #5

Max Range: 0.8341. Min Range: -0.8341

Max Act: 0.7778. Min Act: -0.0000

Data Index: 1200840 (The Pile)

Max Activating Token Index: 626

Text #6

Max Range: 0.8341. Min Range: -0.8341

Max Act: 0.7265. Min Act: -0.0000

Data Index: 1369624 (The Pile)

Max Activating Token Index: 500

Text #7

Max Range: 0.8341. Min Range: -0.8341

Max Act: 0.6541. Min Act: -0.0000

Data Index: 1278853 (The Pile)

Max Activating Token Index: 143

Text #8

Max Range: 0.8341. Min Range: -0.8341

Max Act: 0.7354. Min Act: -0.0000

Data Index: 1299171 (The Pile)

Max Activating Token Index: 244

Text #9

Max Range: 0.8341. Min Range: -0.8341

Max Act: 0.7153. Min Act: -0.0000

Data Index: 1723997 (The Pile)

Max Activating Token Index: 855

Text #10

Max Range: 0.8341. Min Range: -0.8341

Max Act: 0.6727. Min Act: -0.0000

Data Index: 1056043 (The Pile)

Max Activating Token Index: 560

Text #11

Max Range: 0.8341. Min Range: -0.8341

Max Act: 0.6707. Min Act: -0.0000

Data Index: 1859520 (The Pile)

Max Activating Token Index: 55

Text #12

Max Range: 0.8341. Min Range: -0.8341

Max Act: 0.6524. Min Act: -0.0000

Data Index: 1166338 (The Pile)

Max Activating Token Index: 462

Text #13

Max Range: 0.8341. Min Range: -0.8341

Max Act: 0.6694. Min Act: -0.0000

Data Index: 1204202 (The Pile)

Max Activating Token Index: 477

Text #14

Max Range: 0.8341. Min Range: -0.8341

Max Act: 0.6572. Min Act: -0.0000

Data Index: 490289 (The Pile)

Max Activating Token Index: 513

Text #15

Max Range: 0.8341. Min Range: -0.8341

Max Act: 0.6720. Min Act: -0.0000

Data Index: 1916362 (The Pile)

Max Activating Token Index: 30

Text #16

Max Range: 0.8341. Min Range: -0.8341

Max Act: 0.6648. Min Act: -0.0000

Data Index: 1823855 (The Pile)

Max Activating Token Index: 343

Text #17

Max Range: 0.8341. Min Range: -0.8341

Max Act: 0.6749. Min Act: -0.0000

Data Index: 1016585 (The Pile)

Max Activating Token Index: 736

Text #18

Max Range: 0.8341. Min Range: -0.8341

Max Act: 0.6282. Min Act: -0.0000

Data Index: 1362750 (The Pile)

Max Activating Token Index: 63

Text #19

Max Range: 0.8341. Min Range: -0.8341

Max Act: 0.6467. Min Act: -0.0000

Data Index: 426683 (The Pile)

Max Activating Token Index: 907