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

Dataset: The Pile

Neuron 3684 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3624. Min Range: -1.3624

Max Act: 1.3624. Min Act: -0.0000

Data Index: 323639 (The Pile)

Max Activating Token Index: 495

Text #1

Max Range: 1.3624. Min Range: -1.3624

Max Act: 1.2086. Min Act: -0.0000

Data Index: 686844 (The Pile)

Max Activating Token Index: 270

Text #2

Max Range: 1.3624. Min Range: -1.3624

Max Act: 1.1274. Min Act: -0.0000

Data Index: 971760 (The Pile)

Max Activating Token Index: 809

Text #3

Max Range: 1.3624. Min Range: -1.3624

Max Act: 1.0864. Min Act: -0.0000

Data Index: 1073047 (The Pile)

Max Activating Token Index: 473

Text #4

Max Range: 1.3624. Min Range: -1.3624

Max Act: 1.0045. Min Act: -0.0000

Data Index: 955759 (The Pile)

Max Activating Token Index: 963

Text #5

Max Range: 1.3624. Min Range: -1.3624

Max Act: 0.9953. Min Act: -0.0000

Data Index: 1045485 (The Pile)

Max Activating Token Index: 721

Text #6

Max Range: 1.3624. Min Range: -1.3624

Max Act: 1.0378. Min Act: -0.0000

Data Index: 797753 (The Pile)

Max Activating Token Index: 672

Text #7

Max Range: 1.3624. Min Range: -1.3624

Max Act: 0.9549. Min Act: -0.0000

Data Index: 153842 (The Pile)

Max Activating Token Index: 1006

Text #8

Max Range: 1.3624. Min Range: -1.3624

Max Act: 0.9584. Min Act: -0.0000

Data Index: 1427829 (The Pile)

Max Activating Token Index: 176

Text #9

Max Range: 1.3624. Min Range: -1.3624

Max Act: 0.9984. Min Act: -0.0000

Data Index: 1396548 (The Pile)

Max Activating Token Index: 592

Text #10

Max Range: 1.3624. Min Range: -1.3624

Max Act: 0.9487. Min Act: -0.0000

Data Index: 1061666 (The Pile)

Max Activating Token Index: 918

Text #11

Max Range: 1.3624. Min Range: -1.3624

Max Act: 0.9426. Min Act: -0.0000

Data Index: 942188 (The Pile)

Max Activating Token Index: 370

Text #12

Max Range: 1.3624. Min Range: -1.3624

Max Act: 0.9568. Min Act: -0.0000

Data Index: 1631755 (The Pile)

Max Activating Token Index: 678

Text #13

Max Range: 1.3624. Min Range: -1.3624

Max Act: 0.9256. Min Act: -0.0000

Data Index: 151766 (The Pile)

Max Activating Token Index: 105

Text #14

Max Range: 1.3624. Min Range: -1.3624

Max Act: 0.8980. Min Act: -0.0000

Data Index: 1244022 (The Pile)

Max Activating Token Index: 340

Text #15

Max Range: 1.3624. Min Range: -1.3624

Max Act: 0.8831. Min Act: -0.0000

Data Index: 1699327 (The Pile)

Max Activating Token Index: 201

Text #16

Max Range: 1.3624. Min Range: -1.3624

Max Act: 0.9396. Min Act: -0.0000

Data Index: 1984446 (The Pile)

Max Activating Token Index: 868

Text #17

Max Range: 1.3624. Min Range: -1.3624

Max Act: 0.9183. Min Act: -0.0000

Data Index: 1636031 (The Pile)

Max Activating Token Index: 228

Text #18

Max Range: 1.3624. Min Range: -1.3624

Max Act: 0.8637. Min Act: -0.0000

Data Index: 1803558 (The Pile)

Max Activating Token Index: 662

Text #19

Max Range: 1.3624. Min Range: -1.3624

Max Act: 0.8875. Min Act: -0.0000

Data Index: 1368227 (The Pile)

Max Activating Token Index: 268