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

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

Neuron 4631 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0437. Min Range: -1.0437

Max Act: 1.0437. Min Act: -0.0000

Data Index: 1212386 (C4 (Web Text))

Max Activating Token Index: 754

Text #1

Max Range: 1.0437. Min Range: -1.0437

Max Act: 0.8314. Min Act: -0.0000

Data Index: 724517 (C4 (Web Text))

Max Activating Token Index: 961

Text #2

Max Range: 1.0437. Min Range: -1.0437

Max Act: 0.8012. Min Act: -0.0000

Data Index: 1218508 (C4 (Web Text))

Max Activating Token Index: 347

Text #3

Max Range: 1.0437. Min Range: -1.0437

Max Act: 0.8522. Min Act: -0.0000

Data Index: 1127107 (C4 (Web Text))

Max Activating Token Index: 890

Text #4

Max Range: 1.0437. Min Range: -1.0437

Max Act: 0.7380. Min Act: -0.0000

Data Index: 1289783 (C4 (Web Text))

Max Activating Token Index: 937

Text #5

Max Range: 1.0437. Min Range: -1.0437

Max Act: 0.7754. Min Act: -0.0000

Data Index: 268564 (C4 (Web Text))

Max Activating Token Index: 648

Text #6

Max Range: 1.0437. Min Range: -1.0437

Max Act: 0.7102. Min Act: -0.0000

Data Index: 237906 (C4 (Web Text))

Max Activating Token Index: 901

Text #7

Max Range: 1.0437. Min Range: -1.0437

Max Act: 0.6600. Min Act: -0.0000

Data Index: 521920 (C4 (Web Text))

Max Activating Token Index: 500

Text #8

Max Range: 1.0437. Min Range: -1.0437

Max Act: 0.6151. Min Act: -0.0000

Data Index: 178463 (C4 (Web Text))

Max Activating Token Index: 299

Text #9

Max Range: 1.0437. Min Range: -1.0437

Max Act: 0.6568. Min Act: -0.0000

Data Index: 740612 (C4 (Web Text))

Max Activating Token Index: 170

Text #10

Max Range: 1.0437. Min Range: -1.0437

Max Act: 0.6062. Min Act: -0.0000

Data Index: 1117103 (C4 (Web Text))

Max Activating Token Index: 749

Text #11

Max Range: 1.0437. Min Range: -1.0437

Max Act: 0.6186. Min Act: -0.0000

Data Index: 1348999 (C4 (Web Text))

Max Activating Token Index: 568

Text #12

Max Range: 1.0437. Min Range: -1.0437

Max Act: 0.5895. Min Act: -0.0000

Data Index: 1162515 (C4 (Web Text))

Max Activating Token Index: 1011

Text #13

Max Range: 1.0437. Min Range: -1.0437

Max Act: 0.5900. Min Act: -0.0000

Data Index: 701620 (C4 (Web Text))

Max Activating Token Index: 868

Text #14

Max Range: 1.0437. Min Range: -1.0437

Max Act: 0.5743. Min Act: -0.0000

Data Index: 23743 (C4 (Web Text))

Max Activating Token Index: 390

Text #15

Max Range: 1.0437. Min Range: -1.0437

Max Act: 0.5518. Min Act: -0.0000

Data Index: 207014 (C4 (Web Text))

Max Activating Token Index: 727

Text #16

Max Range: 1.0437. Min Range: -1.0437

Max Act: 0.5756. Min Act: -0.0000

Data Index: 730816 (C4 (Web Text))

Max Activating Token Index: 986

Text #17

Max Range: 1.0437. Min Range: -1.0437

Max Act: 0.5887. Min Act: -0.0000

Data Index: 867179 (C4 (Web Text))

Max Activating Token Index: 884

Text #18

Max Range: 1.0437. Min Range: -1.0437

Max Act: 0.6132. Min Act: -0.0000

Data Index: 76130 (C4 (Web Text))

Max Activating Token Index: 638

Text #19

Max Range: 1.0437. Min Range: -1.0437

Max Act: 0.5716. Min Act: -0.0000

Data Index: 1250954 (C4 (Web Text))

Max Activating Token Index: 113