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

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

Neuron 4492 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1687. Min Range: -2.1687

Max Act: 2.1056. Min Act: -0.0000

Data Index: 1339089 (C4 (Web Text))

Max Activating Token Index: 108

Text #1

Max Range: 2.1687. Min Range: -2.1687

Max Act: 2.1511. Min Act: -0.0000

Data Index: 1643876 (Python Code)

Max Activating Token Index: 834

Text #2

Max Range: 2.1687. Min Range: -2.1687

Max Act: 2.1687. Min Act: -0.0000

Data Index: 1266845 (C4 (Web Text))

Max Activating Token Index: 817

Text #3

Max Range: 2.1687. Min Range: -2.1687

Max Act: 2.1456. Min Act: -0.0000

Data Index: 955316 (C4 (Web Text))

Max Activating Token Index: 259

Text #4

Max Range: 2.1687. Min Range: -2.1687

Max Act: 2.1428. Min Act: -0.0000

Data Index: 1552437 (Python Code)

Max Activating Token Index: 744

Text #5

Max Range: 2.1687. Min Range: -2.1687

Max Act: 2.1176. Min Act: -0.0000

Data Index: 759712 (C4 (Web Text))

Max Activating Token Index: 137

Text #6

Max Range: 2.1687. Min Range: -2.1687

Max Act: 2.1156. Min Act: -0.0000

Data Index: 620278 (C4 (Web Text))

Max Activating Token Index: 101

Text #7

Max Range: 2.1687. Min Range: -2.1687

Max Act: 1.9257. Min Act: -0.0000

Data Index: 1091734 (C4 (Web Text))

Max Activating Token Index: 323

Text #8

Max Range: 2.1687. Min Range: -2.1687

Max Act: 1.9211. Min Act: -0.0000

Data Index: 1406178 (Python Code)

Max Activating Token Index: 346

Text #9

Max Range: 2.1687. Min Range: -2.1687

Max Act: 1.9999. Min Act: -0.0000

Data Index: 368671 (C4 (Web Text))

Max Activating Token Index: 352

Text #10

Max Range: 2.1687. Min Range: -2.1687

Max Act: 1.9488. Min Act: -0.0000

Data Index: 1126512 (C4 (Web Text))

Max Activating Token Index: 44

Text #11

Max Range: 2.1687. Min Range: -2.1687

Max Act: 1.9897. Min Act: -0.0000

Data Index: 31291 (C4 (Web Text))

Max Activating Token Index: 206

Text #12

Max Range: 2.1687. Min Range: -2.1687

Max Act: 1.9767. Min Act: -0.0000

Data Index: 959570 (C4 (Web Text))

Max Activating Token Index: 89

Text #13

Max Range: 2.1687. Min Range: -2.1687

Max Act: 2.0180. Min Act: -0.0000

Data Index: 954067 (C4 (Web Text))

Max Activating Token Index: 373

Text #14

Max Range: 2.1687. Min Range: -2.1687

Max Act: 1.9004. Min Act: -0.0000

Data Index: 1329297 (C4 (Web Text))

Max Activating Token Index: 331

Text #15

Max Range: 2.1687. Min Range: -2.1687

Max Act: 1.9958. Min Act: -0.0000

Data Index: 691990 (C4 (Web Text))

Max Activating Token Index: 164

Text #16

Max Range: 2.1687. Min Range: -2.1687

Max Act: 1.9039. Min Act: -0.0000

Data Index: 1466826 (Python Code)

Max Activating Token Index: 135

Text #17

Max Range: 2.1687. Min Range: -2.1687

Max Act: 1.8339. Min Act: -0.0000

Data Index: 290830 (C4 (Web Text))

Max Activating Token Index: 482

Text #18

Max Range: 2.1687. Min Range: -2.1687

Max Act: 1.9786. Min Act: -0.0000

Data Index: 1631747 (Python Code)

Max Activating Token Index: 373

Text #19

Max Range: 2.1687. Min Range: -2.1687

Max Act: 1.8551. Min Act: -0.0000

Data Index: 645622 (C4 (Web Text))

Max Activating Token Index: 445