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

Dataset: The Pile

Neuron 4089 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: 1.7608. Min Range: -1.7608

Max Act: 1.7608. Min Act: -0.0000

Data Index: 1647074 (The Pile)

Max Activating Token Index: 343

Text #1

Max Range: 1.7608. Min Range: -1.7608

Max Act: 1.1294. Min Act: -0.0000

Data Index: 1882820 (The Pile)

Max Activating Token Index: 852

Text #2

Max Range: 1.7608. Min Range: -1.7608

Max Act: 0.9997. Min Act: -0.0000

Data Index: 505123 (The Pile)

Max Activating Token Index: 261

Text #3

Max Range: 1.7608. Min Range: -1.7608

Max Act: 0.9575. Min Act: -0.0000

Data Index: 350458 (The Pile)

Max Activating Token Index: 336

Text #4

Max Range: 1.7608. Min Range: -1.7608

Max Act: 0.8453. Min Act: -0.0000

Data Index: 22314 (The Pile)

Max Activating Token Index: 763

Text #5

Max Range: 1.7608. Min Range: -1.7608

Max Act: 0.8720. Min Act: -0.0000

Data Index: 572006 (The Pile)

Max Activating Token Index: 829

Text #6

Max Range: 1.7608. Min Range: -1.7608

Max Act: 0.8009. Min Act: -0.0000

Data Index: 666782 (The Pile)

Max Activating Token Index: 674

Text #7

Max Range: 1.7608. Min Range: -1.7608

Max Act: 0.8233. Min Act: -0.0000

Data Index: 17396 (The Pile)

Max Activating Token Index: 133

Text #8

Max Range: 1.7608. Min Range: -1.7608

Max Act: 0.7891. Min Act: -0.0000

Data Index: 1042742 (The Pile)

Max Activating Token Index: 324

Text #9

Max Range: 1.7608. Min Range: -1.7608

Max Act: 0.8544. Min Act: -0.0000

Data Index: 386586 (The Pile)

Max Activating Token Index: 499

Text #10

Max Range: 1.7608. Min Range: -1.7608

Max Act: 0.7912. Min Act: -0.0000

Data Index: 1331919 (The Pile)

Max Activating Token Index: 776

Text #11

Max Range: 1.7608. Min Range: -1.7608

Max Act: 0.8260. Min Act: -0.0000

Data Index: 1725780 (The Pile)

Max Activating Token Index: 109

Text #12

Max Range: 1.7608. Min Range: -1.7608

Max Act: 0.7968. Min Act: -0.0000

Data Index: 786907 (The Pile)

Max Activating Token Index: 821

Text #13

Max Range: 1.7608. Min Range: -1.7608

Max Act: 0.8629. Min Act: -0.0000

Data Index: 919667 (The Pile)

Max Activating Token Index: 411

Text #14

Max Range: 1.7608. Min Range: -1.7608

Max Act: 0.8386. Min Act: -0.0000

Data Index: 1178901 (The Pile)

Max Activating Token Index: 199

Text #15

Max Range: 1.7608. Min Range: -1.7608

Max Act: 0.8116. Min Act: -0.0000

Data Index: 1717910 (The Pile)

Max Activating Token Index: 290

Text #16

Max Range: 1.7608. Min Range: -1.7608

Max Act: 0.7787. Min Act: -0.0000

Data Index: 1756100 (The Pile)

Max Activating Token Index: 724

Text #17

Max Range: 1.7608. Min Range: -1.7608

Max Act: 0.8282. Min Act: -0.0000

Data Index: 478136 (The Pile)

Max Activating Token Index: 938

Text #18

Max Range: 1.7608. Min Range: -1.7608

Max Act: 0.7353. Min Act: -0.0000

Data Index: 813464 (The Pile)

Max Activating Token Index: 140

Text #19

Max Range: 1.7608. Min Range: -1.7608

Max Act: 0.7138. Min Act: -0.0000

Data Index: 502648 (The Pile)

Max Activating Token Index: 891