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

Dataset: The Pile

Neuron 4193 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9423. Min Range: -3.9423

Max Act: 3.9423. Min Act: -0.0000

Data Index: 564545 (The Pile)

Max Activating Token Index: 122

Text #1

Max Range: 3.9423. Min Range: -3.9423

Max Act: 3.8111. Min Act: -0.0000

Data Index: 1450164 (The Pile)

Max Activating Token Index: 532

Text #2

Max Range: 3.9423. Min Range: -3.9423

Max Act: 3.4325. Min Act: -0.0000

Data Index: 1298670 (The Pile)

Max Activating Token Index: 874

Text #3

Max Range: 3.9423. Min Range: -3.9423

Max Act: 3.7706. Min Act: -0.0000

Data Index: 1544512 (The Pile)

Max Activating Token Index: 368

Text #4

Max Range: 3.9423. Min Range: -3.9423

Max Act: 3.6736. Min Act: -0.0000

Data Index: 1333082 (The Pile)

Max Activating Token Index: 39

Text #5

Max Range: 3.9423. Min Range: -3.9423

Max Act: 3.6816. Min Act: -0.0000

Data Index: 235001 (The Pile)

Max Activating Token Index: 223

Text #6

Max Range: 3.9423. Min Range: -3.9423

Max Act: 3.1224. Min Act: -0.0000

Data Index: 1674526 (The Pile)

Max Activating Token Index: 961

Text #7

Max Range: 3.9423. Min Range: -3.9423

Max Act: 3.0821. Min Act: -0.0000

Data Index: 146106 (The Pile)

Max Activating Token Index: 242

Text #8

Max Range: 3.9423. Min Range: -3.9423

Max Act: 3.2685. Min Act: -0.0000

Data Index: 739936 (The Pile)

Max Activating Token Index: 224

Text #9

Max Range: 3.9423. Min Range: -3.9423

Max Act: 3.0911. Min Act: -0.0000

Data Index: 296112 (The Pile)

Max Activating Token Index: 227

Text #10

Max Range: 3.9423. Min Range: -3.9423

Max Act: 2.8723. Min Act: -0.0000

Data Index: 1421704 (The Pile)

Max Activating Token Index: 850

Text #11

Max Range: 3.9423. Min Range: -3.9423

Max Act: 2.6874. Min Act: -0.0000

Data Index: 550423 (The Pile)

Max Activating Token Index: 693

Text #12

Max Range: 3.9423. Min Range: -3.9423

Max Act: 2.9825. Min Act: -0.0000

Data Index: 1494984 (The Pile)

Max Activating Token Index: 771

Text #13

Max Range: 3.9423. Min Range: -3.9423

Max Act: 2.8201. Min Act: -0.0000

Data Index: 815280 (The Pile)

Max Activating Token Index: 590

Text #14

Max Range: 3.9423. Min Range: -3.9423

Max Act: 2.9308. Min Act: -0.0000

Data Index: 548956 (The Pile)

Max Activating Token Index: 612

Text #15

Max Range: 3.9423. Min Range: -3.9423

Max Act: 2.7515. Min Act: -0.0000

Data Index: 1572195 (The Pile)

Max Activating Token Index: 141

Text #16

Max Range: 3.9423. Min Range: -3.9423

Max Act: 2.6477. Min Act: -0.0000

Data Index: 248181 (The Pile)

Max Activating Token Index: 95

Text #17

Max Range: 3.9423. Min Range: -3.9423

Max Act: 2.8266. Min Act: -0.0000

Data Index: 1543425 (The Pile)

Max Activating Token Index: 117

Text #18

Max Range: 3.9423. Min Range: -3.9423

Max Act: 2.6725. Min Act: -0.0000

Data Index: 1077631 (The Pile)

Max Activating Token Index: 257

Text #19

Max Range: 3.9423. Min Range: -3.9423

Max Act: 2.7838. Min Act: -0.0000

Data Index: 538752 (The Pile)

Max Activating Token Index: 830