Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 72 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.6772. Min Range: -1.6772

Max Act: 1.6772. Min Act: -0.0000

Data Index: 229675 (The Pile)

Max Activating Token Index: 368

Text #1

Max Range: 1.6772. Min Range: -1.6772

Max Act: 1.5188. Min Act: -0.0000

Data Index: 37040 (The Pile)

Max Activating Token Index: 263

Text #2

Max Range: 1.6772. Min Range: -1.6772

Max Act: 1.2786. Min Act: -0.0000

Data Index: 1019457 (The Pile)

Max Activating Token Index: 844

Text #3

Max Range: 1.6772. Min Range: -1.6772

Max Act: 1.5123. Min Act: -0.0000

Data Index: 1614845 (The Pile)

Max Activating Token Index: 713

Text #4

Max Range: 1.6772. Min Range: -1.6772

Max Act: 1.4806. Min Act: -0.0000

Data Index: 438863 (The Pile)

Max Activating Token Index: 839

Text #5

Max Range: 1.6772. Min Range: -1.6772

Max Act: 1.4744. Min Act: -0.0000

Data Index: 389905 (The Pile)

Max Activating Token Index: 720

Text #6

Max Range: 1.6772. Min Range: -1.6772

Max Act: 1.4085. Min Act: -0.0000

Data Index: 34072 (The Pile)

Max Activating Token Index: 911

Text #7

Max Range: 1.6772. Min Range: -1.6772

Max Act: 1.2904. Min Act: -0.0000

Data Index: 696505 (The Pile)

Max Activating Token Index: 867

Text #8

Max Range: 1.6772. Min Range: -1.6772

Max Act: 1.2912. Min Act: -0.0000

Data Index: 286759 (The Pile)

Max Activating Token Index: 310

Text #9

Max Range: 1.6772. Min Range: -1.6772

Max Act: 1.3316. Min Act: -0.0000

Data Index: 1341537 (The Pile)

Max Activating Token Index: 733

Text #10

Max Range: 1.6772. Min Range: -1.6772

Max Act: 1.2659. Min Act: -0.0000

Data Index: 812237 (The Pile)

Max Activating Token Index: 677

Text #11

Max Range: 1.6772. Min Range: -1.6772

Max Act: 1.3043. Min Act: -0.0000

Data Index: 1622905 (The Pile)

Max Activating Token Index: 766

Text #12

Max Range: 1.6772. Min Range: -1.6772

Max Act: 1.2085. Min Act: -0.0000

Data Index: 345068 (The Pile)

Max Activating Token Index: 992

Text #13

Max Range: 1.6772. Min Range: -1.6772

Max Act: 1.1932. Min Act: -0.0000

Data Index: 1042550 (The Pile)

Max Activating Token Index: 759

Text #14

Max Range: 1.6772. Min Range: -1.6772

Max Act: 1.2205. Min Act: -0.0000

Data Index: 1332264 (The Pile)

Max Activating Token Index: 53

Text #15

Max Range: 1.6772. Min Range: -1.6772

Max Act: 1.2193. Min Act: -0.0000

Data Index: 993921 (The Pile)

Max Activating Token Index: 881

Text #16

Max Range: 1.6772. Min Range: -1.6772

Max Act: 1.1575. Min Act: -0.0000

Data Index: 1648245 (The Pile)

Max Activating Token Index: 540

Text #17

Max Range: 1.6772. Min Range: -1.6772

Max Act: 1.1543. Min Act: -0.0000

Data Index: 303554 (The Pile)

Max Activating Token Index: 154

Text #18

Max Range: 1.6772. Min Range: -1.6772

Max Act: 1.1459. Min Act: -0.0000

Data Index: 490662 (The Pile)

Max Activating Token Index: 1006

Text #19

Max Range: 1.6772. Min Range: -1.6772

Max Act: 1.1350. Min Act: -0.0000

Data Index: 1320287 (The Pile)

Max Activating Token Index: 617