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

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

Neuron 5751 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1728. Min Range: -1.1728

Max Act: 1.1728. Min Act: -0.0000

Data Index: 324373 (C4 (Web Text))

Max Activating Token Index: 436

Text #1

Max Range: 1.1728. Min Range: -1.1728

Max Act: 1.0002. Min Act: -0.0000

Data Index: 552706 (C4 (Web Text))

Max Activating Token Index: 689

Text #2

Max Range: 1.1728. Min Range: -1.1728

Max Act: 1.0453. Min Act: -0.0000

Data Index: 598181 (C4 (Web Text))

Max Activating Token Index: 208

Text #3

Max Range: 1.1728. Min Range: -1.1728

Max Act: 1.0523. Min Act: -0.0000

Data Index: 1046508 (C4 (Web Text))

Max Activating Token Index: 165

Text #4

Max Range: 1.1728. Min Range: -1.1728

Max Act: 0.9006. Min Act: -0.0000

Data Index: 1133353 (C4 (Web Text))

Max Activating Token Index: 944

Text #5

Max Range: 1.1728. Min Range: -1.1728

Max Act: 0.8380. Min Act: -0.0000

Data Index: 402099 (C4 (Web Text))

Max Activating Token Index: 593

Text #6

Max Range: 1.1728. Min Range: -1.1728

Max Act: 0.8714. Min Act: -0.0000

Data Index: 448883 (C4 (Web Text))

Max Activating Token Index: 678

Text #7

Max Range: 1.1728. Min Range: -1.1728

Max Act: 0.8271. Min Act: -0.0000

Data Index: 1395980 (Python Code)

Max Activating Token Index: 56

Text #8

Max Range: 1.1728. Min Range: -1.1728

Max Act: 0.8600. Min Act: -0.0000

Data Index: 491382 (C4 (Web Text))

Max Activating Token Index: 518

Text #9

Max Range: 1.1728. Min Range: -1.1728

Max Act: 0.7967. Min Act: -0.0000

Data Index: 640057 (C4 (Web Text))

Max Activating Token Index: 519

Text #10

Max Range: 1.1728. Min Range: -1.1728

Max Act: 0.8409. Min Act: -0.0000

Data Index: 1328931 (C4 (Web Text))

Max Activating Token Index: 590

Text #11

Max Range: 1.1728. Min Range: -1.1728

Max Act: 0.8219. Min Act: -0.0000

Data Index: 218705 (C4 (Web Text))

Max Activating Token Index: 349

Text #12

Max Range: 1.1728. Min Range: -1.1728

Max Act: 0.7635. Min Act: -0.0000

Data Index: 1563125 (Python Code)

Max Activating Token Index: 74

Text #13

Max Range: 1.1728. Min Range: -1.1728

Max Act: 0.7250. Min Act: -0.0000

Data Index: 145468 (C4 (Web Text))

Max Activating Token Index: 257

Text #14

Max Range: 1.1728. Min Range: -1.1728

Max Act: 0.7686. Min Act: -0.0000

Data Index: 1363470 (Python Code)

Max Activating Token Index: 179

Text #15

Max Range: 1.1728. Min Range: -1.1728

Max Act: 0.7871. Min Act: -0.0000

Data Index: 566880 (C4 (Web Text))

Max Activating Token Index: 503

Text #16

Max Range: 1.1728. Min Range: -1.1728

Max Act: 0.6956. Min Act: -0.0000

Data Index: 24361 (C4 (Web Text))

Max Activating Token Index: 507

Text #17

Max Range: 1.1728. Min Range: -1.1728

Max Act: 0.6431. Min Act: -0.0000

Data Index: 1598697 (Python Code)

Max Activating Token Index: 122

Text #18

Max Range: 1.1728. Min Range: -1.1728

Max Act: 0.6695. Min Act: -0.0000

Data Index: 1611636 (Python Code)

Max Activating Token Index: 430

Text #19

Max Range: 1.1728. Min Range: -1.1728

Max Act: 0.7079. Min Act: -0.0000

Data Index: 1598438 (Python Code)

Max Activating Token Index: 602