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

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

Neuron 4335 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2576. Min Range: -1.2576

Max Act: 1.2576. Min Act: -0.0000

Data Index: 582028 (C4 (Web Text))

Max Activating Token Index: 278

Text #1

Max Range: 1.2576. Min Range: -1.2576

Max Act: 0.9891. Min Act: -0.0000

Data Index: 656339 (C4 (Web Text))

Max Activating Token Index: 348

Text #2

Max Range: 1.2576. Min Range: -1.2576

Max Act: 0.8639. Min Act: -0.0000

Data Index: 751536 (C4 (Web Text))

Max Activating Token Index: 197

Text #3

Max Range: 1.2576. Min Range: -1.2576

Max Act: 0.8824. Min Act: -0.0000

Data Index: 304084 (C4 (Web Text))

Max Activating Token Index: 595

Text #4

Max Range: 1.2576. Min Range: -1.2576

Max Act: 0.9037. Min Act: -0.0000

Data Index: 680010 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 1.2576. Min Range: -1.2576

Max Act: 0.8374. Min Act: -0.0000

Data Index: 318330 (C4 (Web Text))

Max Activating Token Index: 1021

Text #6

Max Range: 1.2576. Min Range: -1.2576

Max Act: 0.8703. Min Act: -0.0000

Data Index: 820437 (C4 (Web Text))

Max Activating Token Index: 746

Text #7

Max Range: 1.2576. Min Range: -1.2576

Max Act: 0.8505. Min Act: -0.0000

Data Index: 999835 (C4 (Web Text))

Max Activating Token Index: 529

Text #8

Max Range: 1.2576. Min Range: -1.2576

Max Act: 0.8812. Min Act: -0.0000

Data Index: 546300 (C4 (Web Text))

Max Activating Token Index: 822

Text #9

Max Range: 1.2576. Min Range: -1.2576

Max Act: 0.8446. Min Act: -0.0000

Data Index: 426573 (C4 (Web Text))

Max Activating Token Index: 378

Text #10

Max Range: 1.2576. Min Range: -1.2576

Max Act: 0.8366. Min Act: -0.0000

Data Index: 552373 (C4 (Web Text))

Max Activating Token Index: 255

Text #11

Max Range: 1.2576. Min Range: -1.2576

Max Act: 0.6995. Min Act: -0.0000

Data Index: 106939 (C4 (Web Text))

Max Activating Token Index: 941

Text #12

Max Range: 1.2576. Min Range: -1.2576

Max Act: 0.7549. Min Act: -0.0000

Data Index: 130899 (C4 (Web Text))

Max Activating Token Index: 590

Text #13

Max Range: 1.2576. Min Range: -1.2576

Max Act: 0.7256. Min Act: -0.0000

Data Index: 382802 (C4 (Web Text))

Max Activating Token Index: 524

Text #14

Max Range: 1.2576. Min Range: -1.2576

Max Act: 0.7629. Min Act: -0.0000

Data Index: 871419 (C4 (Web Text))

Max Activating Token Index: 299

Text #15

Max Range: 1.2576. Min Range: -1.2576

Max Act: 0.7993. Min Act: -0.0000

Data Index: 1141344 (C4 (Web Text))

Max Activating Token Index: 791

Text #16

Max Range: 1.2576. Min Range: -1.2576

Max Act: 0.7803. Min Act: -0.0000

Data Index: 21427 (C4 (Web Text))

Max Activating Token Index: 745

Text #17

Max Range: 1.2576. Min Range: -1.2576

Max Act: 0.7451. Min Act: -0.0000

Data Index: 450548 (C4 (Web Text))

Max Activating Token Index: 494

Text #18

Max Range: 1.2576. Min Range: -1.2576

Max Act: 0.6668. Min Act: -0.0000

Data Index: 660034 (C4 (Web Text))

Max Activating Token Index: 672

Text #19

Max Range: 1.2576. Min Range: -1.2576

Max Act: 0.6910. Min Act: -0.0000

Data Index: 1652704 (Python Code)

Max Activating Token Index: 560