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

Dataset: The Pile

Neuron 122 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4966. Min Range: -3.4966

Max Act: 3.4966. Min Act: -0.0000

Data Index: 242458 (The Pile)

Max Activating Token Index: 687

Text #1

Max Range: 3.4966. Min Range: -3.4966

Max Act: 3.1236. Min Act: -0.0000

Data Index: 23441 (The Pile)

Max Activating Token Index: 862

Text #2

Max Range: 3.4966. Min Range: -3.4966

Max Act: 3.1830. Min Act: -0.0000

Data Index: 840815 (The Pile)

Max Activating Token Index: 575

Text #3

Max Range: 3.4966. Min Range: -3.4966

Max Act: 2.9176. Min Act: -0.0000

Data Index: 186277 (The Pile)

Max Activating Token Index: 820

Text #4

Max Range: 3.4966. Min Range: -3.4966

Max Act: 3.0704. Min Act: -0.0000

Data Index: 1142487 (The Pile)

Max Activating Token Index: 998

Text #5

Max Range: 3.4966. Min Range: -3.4966

Max Act: 2.9159. Min Act: -0.0000

Data Index: 1946819 (The Pile)

Max Activating Token Index: 956

Text #6

Max Range: 3.4966. Min Range: -3.4966

Max Act: 2.7842. Min Act: -0.0000

Data Index: 1729087 (The Pile)

Max Activating Token Index: 836

Text #7

Max Range: 3.4966. Min Range: -3.4966

Max Act: 2.9105. Min Act: -0.0000

Data Index: 1448045 (The Pile)

Max Activating Token Index: 700

Text #8

Max Range: 3.4966. Min Range: -3.4966

Max Act: 2.8362. Min Act: -0.0000

Data Index: 1025606 (The Pile)

Max Activating Token Index: 850

Text #9

Max Range: 3.4966. Min Range: -3.4966

Max Act: 2.9840. Min Act: -0.0000

Data Index: 716571 (The Pile)

Max Activating Token Index: 708

Text #10

Max Range: 3.4966. Min Range: -3.4966

Max Act: 2.8311. Min Act: -0.0000

Data Index: 882918 (The Pile)

Max Activating Token Index: 1022

Text #11

Max Range: 3.4966. Min Range: -3.4966

Max Act: 2.6716. Min Act: -0.0000

Data Index: 491182 (The Pile)

Max Activating Token Index: 565

Text #12

Max Range: 3.4966. Min Range: -3.4966

Max Act: 2.9229. Min Act: -0.0000

Data Index: 1661293 (The Pile)

Max Activating Token Index: 905

Text #13

Max Range: 3.4966. Min Range: -3.4966

Max Act: 2.8361. Min Act: -0.0000

Data Index: 1442888 (The Pile)

Max Activating Token Index: 836

Text #14

Max Range: 3.4966. Min Range: -3.4966

Max Act: 2.5848. Min Act: -0.0000

Data Index: 1352531 (The Pile)

Max Activating Token Index: 952

Text #15

Max Range: 3.4966. Min Range: -3.4966

Max Act: 2.5771. Min Act: -0.0000

Data Index: 1140190 (The Pile)

Max Activating Token Index: 814

Text #16

Max Range: 3.4966. Min Range: -3.4966

Max Act: 2.8199. Min Act: -0.0000

Data Index: 1557361 (The Pile)

Max Activating Token Index: 782

Text #17

Max Range: 3.4966. Min Range: -3.4966

Max Act: 2.7553. Min Act: -0.0000

Data Index: 1483316 (The Pile)

Max Activating Token Index: 643

Text #18

Max Range: 3.4966. Min Range: -3.4966

Max Act: 2.7180. Min Act: -0.0000

Data Index: 1544474 (The Pile)

Max Activating Token Index: 132

Text #19

Max Range: 3.4966. Min Range: -3.4966

Max Act: 2.8409. Min Act: -0.0000

Data Index: 1804961 (The Pile)

Max Activating Token Index: 711