Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 210 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0485. Min Act: -0.0003

Data Index: 1388758 (Python Code)

Max Activating Token Index: 292

Text #1

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0468. Min Act: -0.0003

Data Index: 1137969 (C4 (Web Text))

Max Activating Token Index: 806

Text #2

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0461. Min Act: -0.0003

Data Index: 703842 (C4 (Web Text))

Max Activating Token Index: 574

Text #3

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0458. Min Act: -0.0002

Data Index: 1534713 (Python Code)

Max Activating Token Index: 945

Text #4

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0454. Min Act: -0.0003

Data Index: 1645872 (Python Code)

Max Activating Token Index: 503

Text #5

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0448. Min Act: -0.0002

Data Index: 1463682 (Python Code)

Max Activating Token Index: 766

Text #6

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0445. Min Act: -0.0003

Data Index: 161608 (C4 (Web Text))

Max Activating Token Index: 235

Text #7

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0439. Min Act: -0.0002

Data Index: 1213316 (C4 (Web Text))

Max Activating Token Index: 511

Text #8

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0436. Min Act: -0.0003

Data Index: 624564 (C4 (Web Text))

Max Activating Token Index: 556

Text #9

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0433. Min Act: -0.0002

Data Index: 1320410 (C4 (Web Text))

Max Activating Token Index: 622

Text #10

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0415. Min Act: -0.0003

Data Index: 616670 (C4 (Web Text))

Max Activating Token Index: 907

Text #11

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0446. Min Act: -0.0002

Data Index: 1578921 (Python Code)

Max Activating Token Index: 621

Text #12

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0429. Min Act: -0.0003

Data Index: 425986 (C4 (Web Text))

Max Activating Token Index: 1018

Text #13

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0419. Min Act: -0.0002

Data Index: 1640046 (Python Code)

Max Activating Token Index: 447

Text #14

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0432. Min Act: -0.0003

Data Index: 52588 (C4 (Web Text))

Max Activating Token Index: 942

Text #15

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0433. Min Act: -0.0002

Data Index: 1626442 (Python Code)

Max Activating Token Index: 943

Text #16

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0394. Min Act: -0.0002

Data Index: 600932 (C4 (Web Text))

Max Activating Token Index: 848

Text #17

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0388. Min Act: -0.0002

Data Index: 1525086 (Python Code)

Max Activating Token Index: 871

Text #18

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0404. Min Act: -0.0003

Data Index: 903628 (C4 (Web Text))

Max Activating Token Index: 373

Text #19

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0381. Min Act: -0.0004

Data Index: 552775 (C4 (Web Text))

Max Activating Token Index: 275