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

Dataset: The Pile

Neuron 1444 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: 0.9408. Min Range: -0.9408

Max Act: 0.9408. Min Act: -0.0000

Data Index: 1451367 (The Pile)

Max Activating Token Index: 411

Text #1

Max Range: 0.9408. Min Range: -0.9408

Max Act: 0.9388. Min Act: -0.0000

Data Index: 1111282 (The Pile)

Max Activating Token Index: 870

Text #2

Max Range: 0.9408. Min Range: -0.9408

Max Act: 0.9200. Min Act: -0.0000

Data Index: 712684 (The Pile)

Max Activating Token Index: 790

Text #3

Max Range: 0.9408. Min Range: -0.9408

Max Act: 0.9051. Min Act: -0.0000

Data Index: 520346 (The Pile)

Max Activating Token Index: 455

Text #4

Max Range: 0.9408. Min Range: -0.9408

Max Act: 0.8743. Min Act: -0.0000

Data Index: 86499 (The Pile)

Max Activating Token Index: 800

Text #5

Max Range: 0.9408. Min Range: -0.9408

Max Act: 0.8063. Min Act: -0.0000

Data Index: 1352780 (The Pile)

Max Activating Token Index: 10

Text #6

Max Range: 0.9408. Min Range: -0.9408

Max Act: 0.8020. Min Act: -0.0000

Data Index: 111132 (The Pile)

Max Activating Token Index: 609

Text #7

Max Range: 0.9408. Min Range: -0.9408

Max Act: 0.7191. Min Act: -0.0000

Data Index: 768259 (The Pile)

Max Activating Token Index: 690

Text #8

Max Range: 0.9408. Min Range: -0.9408

Max Act: 0.7396. Min Act: -0.0000

Data Index: 97253 (The Pile)

Max Activating Token Index: 199

Text #9

Max Range: 0.9408. Min Range: -0.9408

Max Act: 0.8359. Min Act: -0.0000

Data Index: 1062198 (The Pile)

Max Activating Token Index: 259

Text #10

Max Range: 0.9408. Min Range: -0.9408

Max Act: 0.7357. Min Act: -0.0000

Data Index: 795526 (The Pile)

Max Activating Token Index: 741

Text #11

Max Range: 0.9408. Min Range: -0.9408

Max Act: 0.8444. Min Act: -0.0000

Data Index: 1684827 (The Pile)

Max Activating Token Index: 680

Text #12

Max Range: 0.9408. Min Range: -0.9408

Max Act: 0.7973. Min Act: -0.0000

Data Index: 16762 (The Pile)

Max Activating Token Index: 936

Text #13

Max Range: 0.9408. Min Range: -0.9408

Max Act: 0.7475. Min Act: -0.0000

Data Index: 632183 (The Pile)

Max Activating Token Index: 132

Text #14

Max Range: 0.9408. Min Range: -0.9408

Max Act: 0.7875. Min Act: -0.0000

Data Index: 62169 (The Pile)

Max Activating Token Index: 872

Text #15

Max Range: 0.9408. Min Range: -0.9408

Max Act: 0.7570. Min Act: -0.0000

Data Index: 1464609 (The Pile)

Max Activating Token Index: 721

Text #16

Max Range: 0.9408. Min Range: -0.9408

Max Act: 0.6519. Min Act: -0.0000

Data Index: 709540 (The Pile)

Max Activating Token Index: 128

Text #17

Max Range: 0.9408. Min Range: -0.9408

Max Act: 0.9368. Min Act: -0.0000

Data Index: 1039824 (The Pile)

Max Activating Token Index: 873

Text #18

Max Range: 0.9408. Min Range: -0.9408

Max Act: 0.7966. Min Act: -0.0000

Data Index: 1999416 (The Pile)

Max Activating Token Index: 13

Text #19

Max Range: 0.9408. Min Range: -0.9408

Max Act: 0.7703. Min Act: -0.0000

Data Index: 1604719 (The Pile)

Max Activating Token Index: 7