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

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

Neuron 2014 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5692. Min Range: -0.5692

Max Act: 0.5692. Min Act: -0.0000

Data Index: 156375 (C4 (Web Text))

Max Activating Token Index: 957

Text #1

Max Range: 0.5692. Min Range: -0.5692

Max Act: 0.4963. Min Act: -0.0000

Data Index: 103499 (C4 (Web Text))

Max Activating Token Index: 857

Text #2

Max Range: 0.5692. Min Range: -0.5692

Max Act: 0.4448. Min Act: -0.0000

Data Index: 1392716 (Python Code)

Max Activating Token Index: 1006

Text #3

Max Range: 0.5692. Min Range: -0.5692

Max Act: 0.3668. Min Act: -0.0000

Data Index: 1539289 (Python Code)

Max Activating Token Index: 536

Text #4

Max Range: 0.5692. Min Range: -0.5692

Max Act: 0.3379. Min Act: -0.0000

Data Index: 344499 (C4 (Web Text))

Max Activating Token Index: 363

Text #5

Max Range: 0.5692. Min Range: -0.5692

Max Act: 0.3306. Min Act: -0.0000

Data Index: 812011 (C4 (Web Text))

Max Activating Token Index: 287

Text #6

Max Range: 0.5692. Min Range: -0.5692

Max Act: 0.3008. Min Act: -0.0000

Data Index: 4734 (C4 (Web Text))

Max Activating Token Index: 874

Text #7

Max Range: 0.5692. Min Range: -0.5692

Max Act: 0.3038. Min Act: -0.0000

Data Index: 766669 (C4 (Web Text))

Max Activating Token Index: 140

Text #8

Max Range: 0.5692. Min Range: -0.5692

Max Act: 0.3022. Min Act: -0.0000

Data Index: 1561954 (Python Code)

Max Activating Token Index: 650

Text #9

Max Range: 0.5692. Min Range: -0.5692

Max Act: 0.3031. Min Act: -0.0000

Data Index: 1332589 (C4 (Web Text))

Max Activating Token Index: 536

Text #10

Max Range: 0.5692. Min Range: -0.5692

Max Act: 0.2972. Min Act: -0.0000

Data Index: 1627713 (Python Code)

Max Activating Token Index: 314

Text #11

Max Range: 0.5692. Min Range: -0.5692

Max Act: 0.2891. Min Act: -0.0000

Data Index: 557676 (C4 (Web Text))

Max Activating Token Index: 333

Text #12

Max Range: 0.5692. Min Range: -0.5692

Max Act: 0.2884. Min Act: -0.0000

Data Index: 1032435 (C4 (Web Text))

Max Activating Token Index: 350

Text #13

Max Range: 0.5692. Min Range: -0.5692

Max Act: 0.2928. Min Act: -0.0000

Data Index: 1336476 (C4 (Web Text))

Max Activating Token Index: 669

Text #14

Max Range: 0.5692. Min Range: -0.5692

Max Act: 0.3014. Min Act: -0.0000

Data Index: 1238304 (C4 (Web Text))

Max Activating Token Index: 539

Text #15

Max Range: 0.5692. Min Range: -0.5692

Max Act: 0.2888. Min Act: -0.0000

Data Index: 1571759 (Python Code)

Max Activating Token Index: 508

Text #16

Max Range: 0.5692. Min Range: -0.5692

Max Act: 0.2752. Min Act: -0.0000

Data Index: 1569218 (Python Code)

Max Activating Token Index: 802

Text #17

Max Range: 0.5692. Min Range: -0.5692

Max Act: 0.2826. Min Act: -0.0000

Data Index: 407165 (C4 (Web Text))

Max Activating Token Index: 839

Text #18

Max Range: 0.5692. Min Range: -0.5692

Max Act: 0.2697. Min Act: -0.0000

Data Index: 1174687 (C4 (Web Text))

Max Activating Token Index: 412

Text #19

Max Range: 0.5692. Min Range: -0.5692

Max Act: 0.2887. Min Act: -0.0000

Data Index: 450845 (C4 (Web Text))

Max Activating Token Index: 771