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

Dataset: The Pile

Neuron 168 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: 0.6528. Min Range: -0.6528

Max Act: 0.6528. Min Act: -0.0000

Data Index: 1823325 (The Pile)

Max Activating Token Index: 260

Text #1

Max Range: 0.6528. Min Range: -0.6528

Max Act: 0.5618. Min Act: -0.0000

Data Index: 160819 (The Pile)

Max Activating Token Index: 49

Text #2

Max Range: 0.6528. Min Range: -0.6528

Max Act: 0.5388. Min Act: -0.0000

Data Index: 1387922 (The Pile)

Max Activating Token Index: 293

Text #3

Max Range: 0.6528. Min Range: -0.6528

Max Act: 0.5075. Min Act: -0.0000

Data Index: 1258891 (The Pile)

Max Activating Token Index: 909

Text #4

Max Range: 0.6528. Min Range: -0.6528

Max Act: 0.4865. Min Act: -0.0000

Data Index: 1520753 (The Pile)

Max Activating Token Index: 873

Text #5

Max Range: 0.6528. Min Range: -0.6528

Max Act: 0.4549. Min Act: -0.0000

Data Index: 93647 (The Pile)

Max Activating Token Index: 693

Text #6

Max Range: 0.6528. Min Range: -0.6528

Max Act: 0.4486. Min Act: -0.0000

Data Index: 1727780 (The Pile)

Max Activating Token Index: 855

Text #7

Max Range: 0.6528. Min Range: -0.6528

Max Act: 0.4457. Min Act: -0.0000

Data Index: 572114 (The Pile)

Max Activating Token Index: 187

Text #8

Max Range: 0.6528. Min Range: -0.6528

Max Act: 0.4422. Min Act: -0.0000

Data Index: 1929112 (The Pile)

Max Activating Token Index: 636

Text #9

Max Range: 0.6528. Min Range: -0.6528

Max Act: 0.4464. Min Act: -0.0000

Data Index: 530429 (The Pile)

Max Activating Token Index: 422

Text #10

Max Range: 0.6528. Min Range: -0.6528

Max Act: 0.4497. Min Act: -0.0000

Data Index: 361341 (The Pile)

Max Activating Token Index: 444

Text #11

Max Range: 0.6528. Min Range: -0.6528

Max Act: 0.4208. Min Act: -0.0000

Data Index: 1652269 (The Pile)

Max Activating Token Index: 278

Text #12

Max Range: 0.6528. Min Range: -0.6528

Max Act: 0.4267. Min Act: -0.0000

Data Index: 1923349 (The Pile)

Max Activating Token Index: 907

Text #13

Max Range: 0.6528. Min Range: -0.6528

Max Act: 0.4068. Min Act: -0.0000

Data Index: 1430180 (The Pile)

Max Activating Token Index: 534

Text #14

Max Range: 0.6528. Min Range: -0.6528

Max Act: 0.3824. Min Act: -0.0000

Data Index: 240850 (The Pile)

Max Activating Token Index: 175

Text #15

Max Range: 0.6528. Min Range: -0.6528

Max Act: 0.3948. Min Act: -0.0000

Data Index: 1727805 (The Pile)

Max Activating Token Index: 145

Text #16

Max Range: 0.6528. Min Range: -0.6528

Max Act: 0.4075. Min Act: -0.0001

Data Index: 230588 (The Pile)

Max Activating Token Index: 355

Text #17

Max Range: 0.6528. Min Range: -0.6528

Max Act: 0.3569. Min Act: -0.0000

Data Index: 594871 (The Pile)

Max Activating Token Index: 660

Text #18

Max Range: 0.6528. Min Range: -0.6528

Max Act: 0.3953. Min Act: -0.0000

Data Index: 1559285 (The Pile)

Max Activating Token Index: 424

Text #19

Max Range: 0.6528. Min Range: -0.6528

Max Act: 0.4170. Min Act: -0.0000

Data Index: 891917 (The Pile)

Max Activating Token Index: 863