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

Dataset: The Pile

Neuron 1310 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: 3.5742. Min Range: -3.5742

Max Act: 3.3994. Min Act: -0.0000

Data Index: 1426622 (The Pile)

Max Activating Token Index: 995

Text #1

Max Range: 3.5742. Min Range: -3.5742

Max Act: 3.4377. Min Act: -0.0000

Data Index: 6546 (The Pile)

Max Activating Token Index: 894

Text #2

Max Range: 3.5742. Min Range: -3.5742

Max Act: 3.2860. Min Act: -0.0000

Data Index: 141644 (The Pile)

Max Activating Token Index: 638

Text #3

Max Range: 3.5742. Min Range: -3.5742

Max Act: 3.5742. Min Act: -0.0000

Data Index: 1214082 (The Pile)

Max Activating Token Index: 650

Text #4

Max Range: 3.5742. Min Range: -3.5742

Max Act: 3.2518. Min Act: -0.0000

Data Index: 400193 (The Pile)

Max Activating Token Index: 959

Text #5

Max Range: 3.5742. Min Range: -3.5742

Max Act: 3.0162. Min Act: -0.0000

Data Index: 368858 (The Pile)

Max Activating Token Index: 778

Text #6

Max Range: 3.5742. Min Range: -3.5742

Max Act: 3.0781. Min Act: -0.0000

Data Index: 650549 (The Pile)

Max Activating Token Index: 271

Text #7

Max Range: 3.5742. Min Range: -3.5742

Max Act: 2.9401. Min Act: -0.0000

Data Index: 1140912 (The Pile)

Max Activating Token Index: 343

Text #8

Max Range: 3.5742. Min Range: -3.5742

Max Act: 3.0248. Min Act: -0.0000

Data Index: 51956 (The Pile)

Max Activating Token Index: 659

Text #9

Max Range: 3.5742. Min Range: -3.5742

Max Act: 3.0238. Min Act: -0.0000

Data Index: 771852 (The Pile)

Max Activating Token Index: 406

Text #10

Max Range: 3.5742. Min Range: -3.5742

Max Act: 2.8842. Min Act: -0.0000

Data Index: 1246221 (The Pile)

Max Activating Token Index: 284

Text #11

Max Range: 3.5742. Min Range: -3.5742

Max Act: 2.9884. Min Act: -0.0000

Data Index: 215236 (The Pile)

Max Activating Token Index: 999

Text #12

Max Range: 3.5742. Min Range: -3.5742

Max Act: 2.8566. Min Act: -0.0000

Data Index: 600585 (The Pile)

Max Activating Token Index: 350

Text #13

Max Range: 3.5742. Min Range: -3.5742

Max Act: 2.8482. Min Act: -0.0000

Data Index: 482096 (The Pile)

Max Activating Token Index: 22

Text #14

Max Range: 3.5742. Min Range: -3.5742

Max Act: 3.1190. Min Act: -0.0000

Data Index: 61740 (The Pile)

Max Activating Token Index: 837

Text #15

Max Range: 3.5742. Min Range: -3.5742

Max Act: 2.8049. Min Act: -0.0000

Data Index: 942100 (The Pile)

Max Activating Token Index: 669

Text #16

Max Range: 3.5742. Min Range: -3.5742

Max Act: 2.7715. Min Act: -0.0000

Data Index: 1768554 (The Pile)

Max Activating Token Index: 308

Text #17

Max Range: 3.5742. Min Range: -3.5742

Max Act: 2.9236. Min Act: -0.0000

Data Index: 1959346 (The Pile)

Max Activating Token Index: 127

Text #18

Max Range: 3.5742. Min Range: -3.5742

Max Act: 2.7273. Min Act: -0.0000

Data Index: 1048924 (The Pile)

Max Activating Token Index: 132

Text #19

Max Range: 3.5742. Min Range: -3.5742

Max Act: 2.8693. Min Act: -0.0000

Data Index: 736245 (The Pile)

Max Activating Token Index: 922