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

Dataset: The Pile

Neuron 4170 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: 0.8533. Min Range: -0.8533

Max Act: 0.8533. Min Act: -0.0000

Data Index: 873822 (The Pile)

Max Activating Token Index: 96

Text #1

Max Range: 0.8533. Min Range: -0.8533

Max Act: 0.6985. Min Act: -0.0000

Data Index: 1867250 (The Pile)

Max Activating Token Index: 713

Text #2

Max Range: 0.8533. Min Range: -0.8533

Max Act: 0.5428. Min Act: -0.0000

Data Index: 1569246 (The Pile)

Max Activating Token Index: 847

Text #3

Max Range: 0.8533. Min Range: -0.8533

Max Act: 0.6747. Min Act: -0.0000

Data Index: 1817989 (The Pile)

Max Activating Token Index: 863

Text #4

Max Range: 0.8533. Min Range: -0.8533

Max Act: 0.7161. Min Act: -0.0000

Data Index: 1864739 (The Pile)

Max Activating Token Index: 590

Text #5

Max Range: 0.8533. Min Range: -0.8533

Max Act: 0.6888. Min Act: -0.0000

Data Index: 1325308 (The Pile)

Max Activating Token Index: 682

Text #6

Max Range: 0.8533. Min Range: -0.8533

Max Act: 0.6520. Min Act: -0.0000

Data Index: 1330077 (The Pile)

Max Activating Token Index: 520

Text #7

Max Range: 0.8533. Min Range: -0.8533

Max Act: 0.6713. Min Act: -0.0000

Data Index: 1671998 (The Pile)

Max Activating Token Index: 334

Text #8

Max Range: 0.8533. Min Range: -0.8533

Max Act: 0.6178. Min Act: -0.0000

Data Index: 1425509 (The Pile)

Max Activating Token Index: 808

Text #9

Max Range: 0.8533. Min Range: -0.8533

Max Act: 0.6371. Min Act: -0.0000

Data Index: 637268 (The Pile)

Max Activating Token Index: 527

Text #10

Max Range: 0.8533. Min Range: -0.8533

Max Act: 0.6578. Min Act: -0.0000

Data Index: 1774963 (The Pile)

Max Activating Token Index: 514

Text #11

Max Range: 0.8533. Min Range: -0.8533

Max Act: 0.5305. Min Act: -0.0000

Data Index: 150539 (The Pile)

Max Activating Token Index: 412

Text #12

Max Range: 0.8533. Min Range: -0.8533

Max Act: 0.5655. Min Act: -0.0000

Data Index: 1472446 (The Pile)

Max Activating Token Index: 694

Text #13

Max Range: 0.8533. Min Range: -0.8533

Max Act: 0.5685. Min Act: -0.0000

Data Index: 1750769 (The Pile)

Max Activating Token Index: 538

Text #14

Max Range: 0.8533. Min Range: -0.8533

Max Act: 0.5444. Min Act: -0.0000

Data Index: 1301487 (The Pile)

Max Activating Token Index: 592

Text #15

Max Range: 0.8533. Min Range: -0.8533

Max Act: 0.5703. Min Act: -0.0000

Data Index: 1856555 (The Pile)

Max Activating Token Index: 745

Text #16

Max Range: 0.8533. Min Range: -0.8533

Max Act: 0.5538. Min Act: -0.0000

Data Index: 88770 (The Pile)

Max Activating Token Index: 258

Text #17

Max Range: 0.8533. Min Range: -0.8533

Max Act: 0.5730. Min Act: -0.0000

Data Index: 1858606 (The Pile)

Max Activating Token Index: 734

Text #18

Max Range: 0.8533. Min Range: -0.8533

Max Act: 0.4935. Min Act: -0.0000

Data Index: 219437 (The Pile)

Max Activating Token Index: 921

Text #19

Max Range: 0.8533. Min Range: -0.8533

Max Act: 0.5225. Min Act: -0.0000

Data Index: 714032 (The Pile)

Max Activating Token Index: 504