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

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

Neuron 1865 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6675. Min Range: -1.6675

Max Act: 1.6359. Min Act: -0.0000

Data Index: 1476449 (Python Code)

Max Activating Token Index: 284

Text #1

Max Range: 1.6675. Min Range: -1.6675

Max Act: 1.4129. Min Act: -0.0000

Data Index: 1140693 (C4 (Web Text))

Max Activating Token Index: 93

Text #2

Max Range: 1.6675. Min Range: -1.6675

Max Act: 1.4990. Min Act: -0.0000

Data Index: 506098 (C4 (Web Text))

Max Activating Token Index: 295

Text #3

Max Range: 1.6675. Min Range: -1.6675

Max Act: 1.6675. Min Act: -0.0000

Data Index: 1449933 (Python Code)

Max Activating Token Index: 332

Text #4

Max Range: 1.6675. Min Range: -1.6675

Max Act: 1.5634. Min Act: -0.0000

Data Index: 57826 (C4 (Web Text))

Max Activating Token Index: 571

Text #5

Max Range: 1.6675. Min Range: -1.6675

Max Act: 1.4443. Min Act: -0.0000

Data Index: 876756 (C4 (Web Text))

Max Activating Token Index: 643

Text #6

Max Range: 1.6675. Min Range: -1.6675

Max Act: 1.4361. Min Act: -0.0000

Data Index: 799545 (C4 (Web Text))

Max Activating Token Index: 753

Text #7

Max Range: 1.6675. Min Range: -1.6675

Max Act: 1.4434. Min Act: -0.0000

Data Index: 292099 (C4 (Web Text))

Max Activating Token Index: 297

Text #8

Max Range: 1.6675. Min Range: -1.6675

Max Act: 1.4571. Min Act: -0.0000

Data Index: 1160227 (C4 (Web Text))

Max Activating Token Index: 672

Text #9

Max Range: 1.6675. Min Range: -1.6675

Max Act: 1.2937. Min Act: -0.0000

Data Index: 1397450 (Python Code)

Max Activating Token Index: 827

Text #10

Max Range: 1.6675. Min Range: -1.6675

Max Act: 1.3609. Min Act: -0.0000

Data Index: 212148 (C4 (Web Text))

Max Activating Token Index: 467

Text #11

Max Range: 1.6675. Min Range: -1.6675

Max Act: 1.3195. Min Act: -0.0000

Data Index: 1405317 (Python Code)

Max Activating Token Index: 210

Text #12

Max Range: 1.6675. Min Range: -1.6675

Max Act: 1.2836. Min Act: -0.0000

Data Index: 1009727 (C4 (Web Text))

Max Activating Token Index: 490

Text #13

Max Range: 1.6675. Min Range: -1.6675

Max Act: 1.3206. Min Act: -0.0000

Data Index: 436504 (C4 (Web Text))

Max Activating Token Index: 381

Text #14

Max Range: 1.6675. Min Range: -1.6675

Max Act: 1.3321. Min Act: -0.0000

Data Index: 742772 (C4 (Web Text))

Max Activating Token Index: 612

Text #15

Max Range: 1.6675. Min Range: -1.6675

Max Act: 1.3376. Min Act: -0.0000

Data Index: 1577884 (Python Code)

Max Activating Token Index: 242

Text #16

Max Range: 1.6675. Min Range: -1.6675

Max Act: 1.2467. Min Act: -0.0000

Data Index: 1090731 (C4 (Web Text))

Max Activating Token Index: 638

Text #17

Max Range: 1.6675. Min Range: -1.6675

Max Act: 1.3044. Min Act: -0.0000

Data Index: 535058 (C4 (Web Text))

Max Activating Token Index: 776

Text #18

Max Range: 1.6675. Min Range: -1.6675

Max Act: 1.2391. Min Act: -0.0000

Data Index: 650840 (C4 (Web Text))

Max Activating Token Index: 906

Text #19

Max Range: 1.6675. Min Range: -1.6675

Max Act: 1.3850. Min Act: -0.0000

Data Index: 1481761 (Python Code)

Max Activating Token Index: 494