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

Dataset: The Pile

Neuron 3592 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: 4.2875. Min Range: -4.2875

Max Act: 4.2466. Min Act: -0.0000

Data Index: 1559352 (The Pile)

Max Activating Token Index: 498

Text #1

Max Range: 4.2875. Min Range: -4.2875

Max Act: 3.8331. Min Act: -0.0000

Data Index: 1323181 (The Pile)

Max Activating Token Index: 82

Text #2

Max Range: 4.2875. Min Range: -4.2875

Max Act: 4.2875. Min Act: -0.0000

Data Index: 1403944 (The Pile)

Max Activating Token Index: 51

Text #3

Max Range: 4.2875. Min Range: -4.2875

Max Act: 3.5868. Min Act: -0.0000

Data Index: 1044818 (The Pile)

Max Activating Token Index: 849

Text #4

Max Range: 4.2875. Min Range: -4.2875

Max Act: 4.0215. Min Act: -0.0000

Data Index: 1866437 (The Pile)

Max Activating Token Index: 133

Text #5

Max Range: 4.2875. Min Range: -4.2875

Max Act: 3.8382. Min Act: -0.0000

Data Index: 1326662 (The Pile)

Max Activating Token Index: 121

Text #6

Max Range: 4.2875. Min Range: -4.2875

Max Act: 3.9706. Min Act: -0.0000

Data Index: 337004 (The Pile)

Max Activating Token Index: 285

Text #7

Max Range: 4.2875. Min Range: -4.2875

Max Act: 3.4810. Min Act: -0.0000

Data Index: 1608425 (The Pile)

Max Activating Token Index: 691

Text #8

Max Range: 4.2875. Min Range: -4.2875

Max Act: 3.4904. Min Act: -0.0000

Data Index: 806815 (The Pile)

Max Activating Token Index: 184

Text #9

Max Range: 4.2875. Min Range: -4.2875

Max Act: 3.5223. Min Act: -0.0000

Data Index: 1792263 (The Pile)

Max Activating Token Index: 512

Text #10

Max Range: 4.2875. Min Range: -4.2875

Max Act: 3.5713. Min Act: -0.0000

Data Index: 710507 (The Pile)

Max Activating Token Index: 810

Text #11

Max Range: 4.2875. Min Range: -4.2875

Max Act: 3.4557. Min Act: -0.0000

Data Index: 1700977 (The Pile)

Max Activating Token Index: 353

Text #12

Max Range: 4.2875. Min Range: -4.2875

Max Act: 3.5643. Min Act: -0.0000

Data Index: 1904063 (The Pile)

Max Activating Token Index: 50

Text #13

Max Range: 4.2875. Min Range: -4.2875

Max Act: 3.4066. Min Act: -0.0000

Data Index: 1985690 (The Pile)

Max Activating Token Index: 34

Text #14

Max Range: 4.2875. Min Range: -4.2875

Max Act: 3.3859. Min Act: -0.0000

Data Index: 1735559 (The Pile)

Max Activating Token Index: 805

Text #15

Max Range: 4.2875. Min Range: -4.2875

Max Act: 3.0731. Min Act: -0.0000

Data Index: 1271122 (The Pile)

Max Activating Token Index: 627

Text #16

Max Range: 4.2875. Min Range: -4.2875

Max Act: 3.1059. Min Act: -0.0000

Data Index: 801075 (The Pile)

Max Activating Token Index: 908

Text #17

Max Range: 4.2875. Min Range: -4.2875

Max Act: 3.2267. Min Act: -0.0000

Data Index: 1038818 (The Pile)

Max Activating Token Index: 364

Text #18

Max Range: 4.2875. Min Range: -4.2875

Max Act: 3.3578. Min Act: -0.0000

Data Index: 525133 (The Pile)

Max Activating Token Index: 784

Text #19

Max Range: 4.2875. Min Range: -4.2875

Max Act: 3.3056. Min Act: -0.0000

Data Index: 816041 (The Pile)

Max Activating Token Index: 376