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

Dataset: The Pile

Neuron 2260 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7080. Min Range: -1.7080

Max Act: 1.7080. Min Act: -0.0000

Data Index: 977498 (The Pile)

Max Activating Token Index: 334

Text #1

Max Range: 1.7080. Min Range: -1.7080

Max Act: 1.5426. Min Act: -0.0000

Data Index: 1391015 (The Pile)

Max Activating Token Index: 395

Text #2

Max Range: 1.7080. Min Range: -1.7080

Max Act: 1.4986. Min Act: -0.0000

Data Index: 1800278 (The Pile)

Max Activating Token Index: 981

Text #3

Max Range: 1.7080. Min Range: -1.7080

Max Act: 1.2931. Min Act: -0.0000

Data Index: 873384 (The Pile)

Max Activating Token Index: 65

Text #4

Max Range: 1.7080. Min Range: -1.7080

Max Act: 1.2746. Min Act: -0.0000

Data Index: 966603 (The Pile)

Max Activating Token Index: 34

Text #5

Max Range: 1.7080. Min Range: -1.7080

Max Act: 1.2078. Min Act: -0.0000

Data Index: 1763093 (The Pile)

Max Activating Token Index: 57

Text #6

Max Range: 1.7080. Min Range: -1.7080

Max Act: 1.1790. Min Act: -0.0000

Data Index: 451520 (The Pile)

Max Activating Token Index: 847

Text #7

Max Range: 1.7080. Min Range: -1.7080

Max Act: 1.1498. Min Act: -0.0000

Data Index: 1631194 (The Pile)

Max Activating Token Index: 381

Text #8

Max Range: 1.7080. Min Range: -1.7080

Max Act: 0.9594. Min Act: -0.0000

Data Index: 1779553 (The Pile)

Max Activating Token Index: 751

Text #9

Max Range: 1.7080. Min Range: -1.7080

Max Act: 0.9308. Min Act: -0.0000

Data Index: 216338 (The Pile)

Max Activating Token Index: 472

Text #10

Max Range: 1.7080. Min Range: -1.7080

Max Act: 0.7808. Min Act: -0.0000

Data Index: 234811 (The Pile)

Max Activating Token Index: 690

Text #11

Max Range: 1.7080. Min Range: -1.7080

Max Act: 0.9159. Min Act: -0.0000

Data Index: 198852 (The Pile)

Max Activating Token Index: 430

Text #12

Max Range: 1.7080. Min Range: -1.7080

Max Act: 0.8907. Min Act: -0.0000

Data Index: 1579017 (The Pile)

Max Activating Token Index: 1006

Text #13

Max Range: 1.7080. Min Range: -1.7080

Max Act: 0.8753. Min Act: -0.0000

Data Index: 280290 (The Pile)

Max Activating Token Index: 690

Text #14

Max Range: 1.7080. Min Range: -1.7080

Max Act: 0.8113. Min Act: -0.0000

Data Index: 243411 (The Pile)

Max Activating Token Index: 58

Text #15

Max Range: 1.7080. Min Range: -1.7080

Max Act: 0.8774. Min Act: -0.0000

Data Index: 245631 (The Pile)

Max Activating Token Index: 704

Text #16

Max Range: 1.7080. Min Range: -1.7080

Max Act: 0.7907. Min Act: -0.0000

Data Index: 1382829 (The Pile)

Max Activating Token Index: 1021

Text #17

Max Range: 1.7080. Min Range: -1.7080

Max Act: 0.8700. Min Act: -0.0000

Data Index: 633451 (The Pile)

Max Activating Token Index: 484

Text #18

Max Range: 1.7080. Min Range: -1.7080

Max Act: 0.8179. Min Act: -0.0000

Data Index: 1753221 (The Pile)

Max Activating Token Index: 556

Text #19

Max Range: 1.7080. Min Range: -1.7080

Max Act: 0.7875. Min Act: -0.0000

Data Index: 1019983 (The Pile)

Max Activating Token Index: 929