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

Dataset: The Pile

Neuron 1226 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0354. Min Range: -1.0354

Max Act: 0.9405. Min Act: -0.0000

Data Index: 1753426 (The Pile)

Max Activating Token Index: 223

Text #1

Max Range: 1.0354. Min Range: -1.0354

Max Act: 1.0354. Min Act: -0.0000

Data Index: 545180 (The Pile)

Max Activating Token Index: 942

Text #2

Max Range: 1.0354. Min Range: -1.0354

Max Act: 0.9152. Min Act: -0.0000

Data Index: 1802063 (The Pile)

Max Activating Token Index: 845

Text #3

Max Range: 1.0354. Min Range: -1.0354

Max Act: 0.9629. Min Act: 0.0000

Data Index: 841396 (The Pile)

Max Activating Token Index: 82

Text #4

Max Range: 1.0354. Min Range: -1.0354

Max Act: 0.9782. Min Act: 0.0000

Data Index: 1912695 (The Pile)

Max Activating Token Index: 185

Text #5

Max Range: 1.0354. Min Range: -1.0354

Max Act: 0.9071. Min Act: -0.0000

Data Index: 1933235 (The Pile)

Max Activating Token Index: 998

Text #6

Max Range: 1.0354. Min Range: -1.0354

Max Act: 0.9360. Min Act: -0.0000

Data Index: 1138480 (The Pile)

Max Activating Token Index: 822

Text #7

Max Range: 1.0354. Min Range: -1.0354

Max Act: 0.9180. Min Act: -0.0000

Data Index: 1023423 (The Pile)

Max Activating Token Index: 932

Text #8

Max Range: 1.0354. Min Range: -1.0354

Max Act: 1.0099. Min Act: -0.0000

Data Index: 888926 (The Pile)

Max Activating Token Index: 438

Text #9

Max Range: 1.0354. Min Range: -1.0354

Max Act: 0.8593. Min Act: -0.0000

Data Index: 691427 (The Pile)

Max Activating Token Index: 820

Text #10

Max Range: 1.0354. Min Range: -1.0354

Max Act: 0.8895. Min Act: -0.0000

Data Index: 323572 (The Pile)

Max Activating Token Index: 751

Text #11

Max Range: 1.0354. Min Range: -1.0354

Max Act: 0.8289. Min Act: -0.0000

Data Index: 1017241 (The Pile)

Max Activating Token Index: 801

Text #12

Max Range: 1.0354. Min Range: -1.0354

Max Act: 0.8597. Min Act: -0.0000

Data Index: 1703045 (The Pile)

Max Activating Token Index: 283

Text #13

Max Range: 1.0354. Min Range: -1.0354

Max Act: 0.9330. Min Act: -0.0000

Data Index: 449644 (The Pile)

Max Activating Token Index: 1004

Text #14

Max Range: 1.0354. Min Range: -1.0354

Max Act: 0.8401. Min Act: -0.0000

Data Index: 1500302 (The Pile)

Max Activating Token Index: 633

Text #15

Max Range: 1.0354. Min Range: -1.0354

Max Act: 0.8795. Min Act: -0.0000

Data Index: 426923 (The Pile)

Max Activating Token Index: 780

Text #16

Max Range: 1.0354. Min Range: -1.0354

Max Act: 0.8160. Min Act: -0.0000

Data Index: 815880 (The Pile)

Max Activating Token Index: 767

Text #17

Max Range: 1.0354. Min Range: -1.0354

Max Act: 0.8387. Min Act: -0.0000

Data Index: 1812471 (The Pile)

Max Activating Token Index: 971

Text #18

Max Range: 1.0354. Min Range: -1.0354

Max Act: 0.8182. Min Act: -0.0000

Data Index: 1154534 (The Pile)

Max Activating Token Index: 408

Text #19

Max Range: 1.0354. Min Range: -1.0354

Max Act: 0.7847. Min Act: -0.0000

Data Index: 1475714 (The Pile)

Max Activating Token Index: 540