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

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

Neuron 1871 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0904. Min Act: -0.0002

Data Index: 517526 (C4 (Web Text))

Max Activating Token Index: 575

Text #1

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0877. Min Act: -0.0002

Data Index: 209101 (C4 (Web Text))

Max Activating Token Index: 261

Text #2

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0799. Min Act: -0.0002

Data Index: 541681 (C4 (Web Text))

Max Activating Token Index: 227

Text #3

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0693. Min Act: -0.0002

Data Index: 1098615 (C4 (Web Text))

Max Activating Token Index: 164

Text #4

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0706. Min Act: -0.0002

Data Index: 712886 (C4 (Web Text))

Max Activating Token Index: 395

Text #5

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0674. Min Act: -0.0002

Data Index: 195036 (C4 (Web Text))

Max Activating Token Index: 162

Text #6

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0729. Min Act: -0.0002

Data Index: 444557 (C4 (Web Text))

Max Activating Token Index: 301

Text #7

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0626. Min Act: -0.0002

Data Index: 630228 (C4 (Web Text))

Max Activating Token Index: 547

Text #8

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0572. Min Act: -0.0002

Data Index: 97318 (C4 (Web Text))

Max Activating Token Index: 45

Text #9

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0567. Min Act: -0.0002

Data Index: 646869 (C4 (Web Text))

Max Activating Token Index: 646

Text #10

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0565. Min Act: -0.0002

Data Index: 437954 (C4 (Web Text))

Max Activating Token Index: 382

Text #11

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0559. Min Act: -0.0002

Data Index: 719590 (C4 (Web Text))

Max Activating Token Index: 936

Text #12

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0537. Min Act: -0.0002

Data Index: 1027009 (C4 (Web Text))

Max Activating Token Index: 950

Text #13

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0558. Min Act: -0.0002

Data Index: 966647 (C4 (Web Text))

Max Activating Token Index: 595

Text #14

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0558. Min Act: -0.0002

Data Index: 1000932 (C4 (Web Text))

Max Activating Token Index: 223

Text #15

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0555. Min Act: -0.0002

Data Index: 445136 (C4 (Web Text))

Max Activating Token Index: 121

Text #16

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0519. Min Act: -0.0002

Data Index: 369729 (C4 (Web Text))

Max Activating Token Index: 873

Text #17

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0509. Min Act: -0.0002

Data Index: 681868 (C4 (Web Text))

Max Activating Token Index: 407

Text #18

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0560. Min Act: -0.0002

Data Index: 73576 (C4 (Web Text))

Max Activating Token Index: 393

Text #19

Max Range: 0.0904. Min Range: -0.0904

Max Act: 0.0521. Min Act: -0.0002

Data Index: 1271448 (C4 (Web Text))

Max Activating Token Index: 643