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

Dataset: The Pile

Neuron 3569 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3024. Min Range: -1.3024

Max Act: 1.3024. Min Act: -0.0000

Data Index: 1981889 (The Pile)

Max Activating Token Index: 561

Text #1

Max Range: 1.3024. Min Range: -1.3024

Max Act: 1.0784. Min Act: -0.0000

Data Index: 793941 (The Pile)

Max Activating Token Index: 881

Text #2

Max Range: 1.3024. Min Range: -1.3024

Max Act: 1.0448. Min Act: -0.0000

Data Index: 1959843 (The Pile)

Max Activating Token Index: 544

Text #3

Max Range: 1.3024. Min Range: -1.3024

Max Act: 0.9897. Min Act: -0.0000

Data Index: 1760267 (The Pile)

Max Activating Token Index: 762

Text #4

Max Range: 1.3024. Min Range: -1.3024

Max Act: 0.9576. Min Act: -0.0000

Data Index: 693593 (The Pile)

Max Activating Token Index: 838

Text #5

Max Range: 1.3024. Min Range: -1.3024

Max Act: 0.8878. Min Act: -0.0000

Data Index: 1247085 (The Pile)

Max Activating Token Index: 174

Text #6

Max Range: 1.3024. Min Range: -1.3024

Max Act: 0.8503. Min Act: -0.0000

Data Index: 660791 (The Pile)

Max Activating Token Index: 948

Text #7

Max Range: 1.3024. Min Range: -1.3024

Max Act: 0.8797. Min Act: -0.0000

Data Index: 737325 (The Pile)

Max Activating Token Index: 429

Text #8

Max Range: 1.3024. Min Range: -1.3024

Max Act: 0.8483. Min Act: -0.0000

Data Index: 1989521 (The Pile)

Max Activating Token Index: 282

Text #9

Max Range: 1.3024. Min Range: -1.3024

Max Act: 0.9021. Min Act: -0.0000

Data Index: 946203 (The Pile)

Max Activating Token Index: 459

Text #10

Max Range: 1.3024. Min Range: -1.3024

Max Act: 0.8422. Min Act: -0.0000

Data Index: 344286 (The Pile)

Max Activating Token Index: 334

Text #11

Max Range: 1.3024. Min Range: -1.3024

Max Act: 0.9053. Min Act: -0.0000

Data Index: 862634 (The Pile)

Max Activating Token Index: 850

Text #12

Max Range: 1.3024. Min Range: -1.3024

Max Act: 0.8519. Min Act: -0.0000

Data Index: 1479047 (The Pile)

Max Activating Token Index: 458

Text #13

Max Range: 1.3024. Min Range: -1.3024

Max Act: 0.7978. Min Act: -0.0000

Data Index: 694893 (The Pile)

Max Activating Token Index: 371

Text #14

Max Range: 1.3024. Min Range: -1.3024

Max Act: 0.7987. Min Act: -0.0000

Data Index: 1419930 (The Pile)

Max Activating Token Index: 599

Text #15

Max Range: 1.3024. Min Range: -1.3024

Max Act: 0.8287. Min Act: -0.0000

Data Index: 1397006 (The Pile)

Max Activating Token Index: 517

Text #16

Max Range: 1.3024. Min Range: -1.3024

Max Act: 0.8477. Min Act: -0.0000

Data Index: 1455531 (The Pile)

Max Activating Token Index: 667

Text #17

Max Range: 1.3024. Min Range: -1.3024

Max Act: 0.7903. Min Act: -0.0000

Data Index: 1498206 (The Pile)

Max Activating Token Index: 157

Text #18

Max Range: 1.3024. Min Range: -1.3024

Max Act: 0.7846. Min Act: -0.0000

Data Index: 744453 (The Pile)

Max Activating Token Index: 947

Text #19

Max Range: 1.3024. Min Range: -1.3024

Max Act: 0.7993. Min Act: -0.0000

Data Index: 828464 (The Pile)

Max Activating Token Index: 384