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

Dataset: The Pile

Neuron 4913 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: 1.8459. Min Range: -1.8459

Max Act: 1.8459. Min Act: -0.0000

Data Index: 125066 (The Pile)

Max Activating Token Index: 500

Text #1

Max Range: 1.8459. Min Range: -1.8459

Max Act: 1.6656. Min Act: -0.0000

Data Index: 1822455 (The Pile)

Max Activating Token Index: 407

Text #2

Max Range: 1.8459. Min Range: -1.8459

Max Act: 1.6153. Min Act: -0.0000

Data Index: 1462734 (The Pile)

Max Activating Token Index: 436

Text #3

Max Range: 1.8459. Min Range: -1.8459

Max Act: 1.6100. Min Act: -0.0000

Data Index: 1814855 (The Pile)

Max Activating Token Index: 550

Text #4

Max Range: 1.8459. Min Range: -1.8459

Max Act: 1.6827. Min Act: -0.0000

Data Index: 1281261 (The Pile)

Max Activating Token Index: 412

Text #5

Max Range: 1.8459. Min Range: -1.8459

Max Act: 1.5907. Min Act: -0.0000

Data Index: 190793 (The Pile)

Max Activating Token Index: 678

Text #6

Max Range: 1.8459. Min Range: -1.8459

Max Act: 1.5633. Min Act: -0.0000

Data Index: 1952938 (The Pile)

Max Activating Token Index: 550

Text #7

Max Range: 1.8459. Min Range: -1.8459

Max Act: 1.6080. Min Act: -0.0000

Data Index: 819388 (The Pile)

Max Activating Token Index: 386

Text #8

Max Range: 1.8459. Min Range: -1.8459

Max Act: 1.6890. Min Act: -0.0000

Data Index: 1077524 (The Pile)

Max Activating Token Index: 73

Text #9

Max Range: 1.8459. Min Range: -1.8459

Max Act: 1.4904. Min Act: -0.0000

Data Index: 1962756 (The Pile)

Max Activating Token Index: 280

Text #10

Max Range: 1.8459. Min Range: -1.8459

Max Act: 1.5789. Min Act: -0.0000

Data Index: 1493067 (The Pile)

Max Activating Token Index: 718

Text #11

Max Range: 1.8459. Min Range: -1.8459

Max Act: 1.5311. Min Act: -0.0000

Data Index: 1893870 (The Pile)

Max Activating Token Index: 688

Text #12

Max Range: 1.8459. Min Range: -1.8459

Max Act: 1.5307. Min Act: -0.0000

Data Index: 375224 (The Pile)

Max Activating Token Index: 400

Text #13

Max Range: 1.8459. Min Range: -1.8459

Max Act: 1.5748. Min Act: -0.0000

Data Index: 822462 (The Pile)

Max Activating Token Index: 371

Text #14

Max Range: 1.8459. Min Range: -1.8459

Max Act: 1.4695. Min Act: -0.0000

Data Index: 1505544 (The Pile)

Max Activating Token Index: 264

Text #15

Max Range: 1.8459. Min Range: -1.8459

Max Act: 1.4235. Min Act: -0.0000

Data Index: 912401 (The Pile)

Max Activating Token Index: 658

Text #16

Max Range: 1.8459. Min Range: -1.8459

Max Act: 1.5106. Min Act: -0.0000

Data Index: 1634001 (The Pile)

Max Activating Token Index: 446

Text #17

Max Range: 1.8459. Min Range: -1.8459

Max Act: 1.4143. Min Act: -0.0000

Data Index: 129991 (The Pile)

Max Activating Token Index: 511

Text #18

Max Range: 1.8459. Min Range: -1.8459

Max Act: 1.5378. Min Act: -0.0000

Data Index: 378750 (The Pile)

Max Activating Token Index: 540

Text #19

Max Range: 1.8459. Min Range: -1.8459

Max Act: 1.4477. Min Act: -0.0000

Data Index: 1384670 (The Pile)

Max Activating Token Index: 603