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

Dataset: The Pile

Neuron 4410 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0329. Min Range: -1.0329

Max Act: 1.0329. Min Act: -0.0000

Data Index: 60910 (The Pile)

Max Activating Token Index: 704

Text #1

Max Range: 1.0329. Min Range: -1.0329

Max Act: 0.9346. Min Act: -0.0000

Data Index: 538681 (The Pile)

Max Activating Token Index: 538

Text #2

Max Range: 1.0329. Min Range: -1.0329

Max Act: 0.8702. Min Act: -0.0000

Data Index: 1005335 (The Pile)

Max Activating Token Index: 660

Text #3

Max Range: 1.0329. Min Range: -1.0329

Max Act: 0.7898. Min Act: -0.0000

Data Index: 1197700 (The Pile)

Max Activating Token Index: 533

Text #4

Max Range: 1.0329. Min Range: -1.0329

Max Act: 0.9217. Min Act: -0.0000

Data Index: 382924 (The Pile)

Max Activating Token Index: 570

Text #5

Max Range: 1.0329. Min Range: -1.0329

Max Act: 0.8527. Min Act: -0.0000

Data Index: 1490115 (The Pile)

Max Activating Token Index: 726

Text #6

Max Range: 1.0329. Min Range: -1.0329

Max Act: 0.7969. Min Act: -0.0000

Data Index: 934781 (The Pile)

Max Activating Token Index: 393

Text #7

Max Range: 1.0329. Min Range: -1.0329

Max Act: 0.8073. Min Act: -0.0000

Data Index: 185303 (The Pile)

Max Activating Token Index: 463

Text #8

Max Range: 1.0329. Min Range: -1.0329

Max Act: 0.7714. Min Act: -0.0000

Data Index: 1853424 (The Pile)

Max Activating Token Index: 938

Text #9

Max Range: 1.0329. Min Range: -1.0329

Max Act: 0.7458. Min Act: -0.0000

Data Index: 1448486 (The Pile)

Max Activating Token Index: 157

Text #10

Max Range: 1.0329. Min Range: -1.0329

Max Act: 0.7921. Min Act: -0.0000

Data Index: 561329 (The Pile)

Max Activating Token Index: 76

Text #11

Max Range: 1.0329. Min Range: -1.0329

Max Act: 0.7569. Min Act: -0.0000

Data Index: 737389 (The Pile)

Max Activating Token Index: 733

Text #12

Max Range: 1.0329. Min Range: -1.0329

Max Act: 0.7582. Min Act: -0.0000

Data Index: 945956 (The Pile)

Max Activating Token Index: 699

Text #13

Max Range: 1.0329. Min Range: -1.0329

Max Act: 0.6854. Min Act: -0.0000

Data Index: 27102 (The Pile)

Max Activating Token Index: 315

Text #14

Max Range: 1.0329. Min Range: -1.0329

Max Act: 0.6772. Min Act: -0.0000

Data Index: 861022 (The Pile)

Max Activating Token Index: 416

Text #15

Max Range: 1.0329. Min Range: -1.0329

Max Act: 0.6746. Min Act: -0.0000

Data Index: 1649939 (The Pile)

Max Activating Token Index: 195

Text #16

Max Range: 1.0329. Min Range: -1.0329

Max Act: 0.6784. Min Act: -0.0000

Data Index: 728999 (The Pile)

Max Activating Token Index: 303

Text #17

Max Range: 1.0329. Min Range: -1.0329

Max Act: 0.6312. Min Act: -0.0000

Data Index: 203437 (The Pile)

Max Activating Token Index: 262

Text #18

Max Range: 1.0329. Min Range: -1.0329

Max Act: 0.6313. Min Act: -0.0000

Data Index: 711676 (The Pile)

Max Activating Token Index: 810

Text #19

Max Range: 1.0329. Min Range: -1.0329

Max Act: 0.6598. Min Act: -0.0000

Data Index: 379048 (The Pile)

Max Activating Token Index: 298