Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 170 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.3170. Min Range: -2.3170

Max Act: 2.3170. Min Act: -0.0000

Data Index: 307887 (C4 (Web Text))

Max Activating Token Index: 851

Text #1

Max Range: 2.3170. Min Range: -2.3170

Max Act: 2.0731. Min Act: -0.0000

Data Index: 582764 (C4 (Web Text))

Max Activating Token Index: 26

Text #2

Max Range: 2.3170. Min Range: -2.3170

Max Act: 1.9634. Min Act: -0.0000

Data Index: 875619 (C4 (Web Text))

Max Activating Token Index: 531

Text #3

Max Range: 2.3170. Min Range: -2.3170

Max Act: 1.9586. Min Act: -0.0000

Data Index: 458171 (C4 (Web Text))

Max Activating Token Index: 466

Text #4

Max Range: 2.3170. Min Range: -2.3170

Max Act: 2.0135. Min Act: -0.0000

Data Index: 586427 (C4 (Web Text))

Max Activating Token Index: 488

Text #5

Max Range: 2.3170. Min Range: -2.3170

Max Act: 1.8904. Min Act: -0.0000

Data Index: 840078 (C4 (Web Text))

Max Activating Token Index: 111

Text #6

Max Range: 2.3170. Min Range: -2.3170

Max Act: 1.7598. Min Act: -0.0000

Data Index: 1643071 (Python Code)

Max Activating Token Index: 906

Text #7

Max Range: 2.3170. Min Range: -2.3170

Max Act: 1.7778. Min Act: -0.0000

Data Index: 1402266 (Python Code)

Max Activating Token Index: 929

Text #8

Max Range: 2.3170. Min Range: -2.3170

Max Act: 1.8085. Min Act: -0.0000

Data Index: 1418747 (Python Code)

Max Activating Token Index: 864

Text #9

Max Range: 2.3170. Min Range: -2.3170

Max Act: 1.6887. Min Act: -0.0000

Data Index: 803656 (C4 (Web Text))

Max Activating Token Index: 319

Text #10

Max Range: 2.3170. Min Range: -2.3170

Max Act: 1.8332. Min Act: -0.0000

Data Index: 1617480 (Python Code)

Max Activating Token Index: 678

Text #11

Max Range: 2.3170. Min Range: -2.3170

Max Act: 1.7874. Min Act: -0.0000

Data Index: 1087087 (C4 (Web Text))

Max Activating Token Index: 464

Text #12

Max Range: 2.3170. Min Range: -2.3170

Max Act: 1.7816. Min Act: -0.0000

Data Index: 1446177 (Python Code)

Max Activating Token Index: 575

Text #13

Max Range: 2.3170. Min Range: -2.3170

Max Act: 1.7775. Min Act: -0.0000

Data Index: 1437088 (Python Code)

Max Activating Token Index: 728

Text #14

Max Range: 2.3170. Min Range: -2.3170

Max Act: 1.7725. Min Act: -0.0000

Data Index: 1570148 (Python Code)

Max Activating Token Index: 763

Text #15

Max Range: 2.3170. Min Range: -2.3170

Max Act: 1.7044. Min Act: -0.0000

Data Index: 1391671 (Python Code)

Max Activating Token Index: 872

Text #16

Max Range: 2.3170. Min Range: -2.3170

Max Act: 1.7235. Min Act: -0.0000

Data Index: 1582393 (Python Code)

Max Activating Token Index: 557

Text #17

Max Range: 2.3170. Min Range: -2.3170

Max Act: 1.7241. Min Act: -0.0000

Data Index: 1636506 (Python Code)

Max Activating Token Index: 622

Text #18

Max Range: 2.3170. Min Range: -2.3170

Max Act: 1.6757. Min Act: -0.0000

Data Index: 1447506 (Python Code)

Max Activating Token Index: 753

Text #19

Max Range: 2.3170. Min Range: -2.3170

Max Act: 1.6699. Min Act: -0.0000

Data Index: 1642125 (Python Code)

Max Activating Token Index: 672