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

Dataset: The Pile

Neuron 548 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: 0.9498. Min Range: -0.9498

Max Act: 0.9498. Min Act: -0.0000

Data Index: 785564 (The Pile)

Max Activating Token Index: 788

Text #1

Max Range: 0.9498. Min Range: -0.9498

Max Act: 0.7291. Min Act: -0.0000

Data Index: 1357234 (The Pile)

Max Activating Token Index: 268

Text #2

Max Range: 0.9498. Min Range: -0.9498

Max Act: 0.6586. Min Act: -0.0000

Data Index: 503286 (The Pile)

Max Activating Token Index: 960

Text #3

Max Range: 0.9498. Min Range: -0.9498

Max Act: 0.6515. Min Act: -0.0000

Data Index: 895815 (The Pile)

Max Activating Token Index: 812

Text #4

Max Range: 0.9498. Min Range: -0.9498

Max Act: 0.5745. Min Act: -0.0000

Data Index: 1527581 (The Pile)

Max Activating Token Index: 706

Text #5

Max Range: 0.9498. Min Range: -0.9498

Max Act: 0.5477. Min Act: -0.0000

Data Index: 1007814 (The Pile)

Max Activating Token Index: 357

Text #6

Max Range: 0.9498. Min Range: -0.9498

Max Act: 0.5840. Min Act: -0.0000

Data Index: 1564765 (The Pile)

Max Activating Token Index: 713

Text #7

Max Range: 0.9498. Min Range: -0.9498

Max Act: 0.5423. Min Act: -0.0000

Data Index: 1785742 (The Pile)

Max Activating Token Index: 193

Text #8

Max Range: 0.9498. Min Range: -0.9498

Max Act: 0.5134. Min Act: -0.0000

Data Index: 309226 (The Pile)

Max Activating Token Index: 804

Text #9

Max Range: 0.9498. Min Range: -0.9498

Max Act: 0.5684. Min Act: -0.0000

Data Index: 360202 (The Pile)

Max Activating Token Index: 919

Text #10

Max Range: 0.9498. Min Range: -0.9498

Max Act: 0.4991. Min Act: -0.0000

Data Index: 940554 (The Pile)

Max Activating Token Index: 1008

Text #11

Max Range: 0.9498. Min Range: -0.9498

Max Act: 0.4941. Min Act: -0.0000

Data Index: 416197 (The Pile)

Max Activating Token Index: 368

Text #12

Max Range: 0.9498. Min Range: -0.9498

Max Act: 0.5395. Min Act: -0.0000

Data Index: 1285215 (The Pile)

Max Activating Token Index: 622

Text #13

Max Range: 0.9498. Min Range: -0.9498

Max Act: 0.4685. Min Act: -0.0000

Data Index: 1986442 (The Pile)

Max Activating Token Index: 954

Text #14

Max Range: 0.9498. Min Range: -0.9498

Max Act: 0.4672. Min Act: -0.0000

Data Index: 175470 (The Pile)

Max Activating Token Index: 1001

Text #15

Max Range: 0.9498. Min Range: -0.9498

Max Act: 0.4476. Min Act: -0.0000

Data Index: 1773736 (The Pile)

Max Activating Token Index: 344

Text #16

Max Range: 0.9498. Min Range: -0.9498

Max Act: 0.4845. Min Act: -0.0000

Data Index: 1663152 (The Pile)

Max Activating Token Index: 523

Text #17

Max Range: 0.9498. Min Range: -0.9498

Max Act: 0.5296. Min Act: -0.0000

Data Index: 1535582 (The Pile)

Max Activating Token Index: 331

Text #18

Max Range: 0.9498. Min Range: -0.9498

Max Act: 0.4625. Min Act: -0.0000

Data Index: 329587 (The Pile)

Max Activating Token Index: 1022

Text #19

Max Range: 0.9498. Min Range: -0.9498

Max Act: 0.5060. Min Act: -0.0000

Data Index: 1890517 (The Pile)

Max Activating Token Index: 596