Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 4062 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0897. Min Act: -0.0000

Data Index: 99447 (C4 (Web Text))

Max Activating Token Index: 530

Text #1

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0967. Min Act: -0.0001

Data Index: 345868 (C4 (Web Text))

Max Activating Token Index: 724

Text #2

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0893. Min Act: -0.0001

Data Index: 160909 (C4 (Web Text))

Max Activating Token Index: 562

Text #3

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0857. Min Act: -0.0001

Data Index: 485192 (C4 (Web Text))

Max Activating Token Index: 875

Text #4

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0888. Min Act: -0.0000

Data Index: 1178102 (C4 (Web Text))

Max Activating Token Index: 555

Text #5

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0818. Min Act: -0.0001

Data Index: 894745 (C4 (Web Text))

Max Activating Token Index: 768

Text #6

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0849. Min Act: -0.0000

Data Index: 615820 (C4 (Web Text))

Max Activating Token Index: 614

Text #7

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0819. Min Act: -0.0001

Data Index: 621621 (C4 (Web Text))

Max Activating Token Index: 64

Text #8

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0815. Min Act: -0.0001

Data Index: 1119776 (C4 (Web Text))

Max Activating Token Index: 658

Text #9

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0831. Min Act: -0.0001

Data Index: 9824 (C4 (Web Text))

Max Activating Token Index: 546

Text #10

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0822. Min Act: -0.0001

Data Index: 379529 (C4 (Web Text))

Max Activating Token Index: 427

Text #11

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0837. Min Act: -0.0000

Data Index: 344510 (C4 (Web Text))

Max Activating Token Index: 649

Text #12

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0767. Min Act: -0.0001

Data Index: 510359 (C4 (Web Text))

Max Activating Token Index: 781

Text #13

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0786. Min Act: -0.0001

Data Index: 86770 (C4 (Web Text))

Max Activating Token Index: 685

Text #14

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0752. Min Act: -0.0001

Data Index: 495827 (C4 (Web Text))

Max Activating Token Index: 590

Text #15

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0839. Min Act: -0.0000

Data Index: 503821 (C4 (Web Text))

Max Activating Token Index: 865

Text #16

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0733. Min Act: -0.0001

Data Index: 56575 (C4 (Web Text))

Max Activating Token Index: 629

Text #17

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0716. Min Act: -0.0000

Data Index: 225466 (C4 (Web Text))

Max Activating Token Index: 136

Text #18

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0708. Min Act: -0.0001

Data Index: 1352430 (C4 (Web Text))

Max Activating Token Index: 628

Text #19

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0697. Min Act: -0.0001

Data Index: 1092490 (C4 (Web Text))

Max Activating Token Index: 668