Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 898 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0483. Min Act: -0.0006

Data Index: 76680 (C4 (Web Text))

Max Activating Token Index: 769

Text #1

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0485. Min Act: -0.0006

Data Index: 369342 (C4 (Web Text))

Max Activating Token Index: 643

Text #2

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0460. Min Act: -0.0006

Data Index: 221966 (C4 (Web Text))

Max Activating Token Index: 84

Text #3

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0451. Min Act: -0.0006

Data Index: 279909 (C4 (Web Text))

Max Activating Token Index: 492

Text #4

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0449. Min Act: -0.0006

Data Index: 1322095 (C4 (Web Text))

Max Activating Token Index: 524

Text #5

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0446. Min Act: -0.0006

Data Index: 1205786 (C4 (Web Text))

Max Activating Token Index: 940

Text #6

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0434. Min Act: -0.0006

Data Index: 638550 (C4 (Web Text))

Max Activating Token Index: 517

Text #7

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0429. Min Act: -0.0006

Data Index: 686025 (C4 (Web Text))

Max Activating Token Index: 56

Text #8

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0430. Min Act: -0.0006

Data Index: 943741 (C4 (Web Text))

Max Activating Token Index: 588

Text #9

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0428. Min Act: -0.0006

Data Index: 434662 (C4 (Web Text))

Max Activating Token Index: 368

Text #10

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0413. Min Act: -0.0006

Data Index: 212136 (C4 (Web Text))

Max Activating Token Index: 75

Text #11

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0419. Min Act: -0.0006

Data Index: 1240503 (C4 (Web Text))

Max Activating Token Index: 177

Text #12

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0410. Min Act: -0.0006

Data Index: 100897 (C4 (Web Text))

Max Activating Token Index: 35

Text #13

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0412. Min Act: -0.0006

Data Index: 1018835 (C4 (Web Text))

Max Activating Token Index: 27

Text #14

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0400. Min Act: -0.0006

Data Index: 31077 (C4 (Web Text))

Max Activating Token Index: 452

Text #15

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0393. Min Act: -0.0006

Data Index: 603691 (C4 (Web Text))

Max Activating Token Index: 574

Text #16

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0401. Min Act: -0.0006

Data Index: 294779 (C4 (Web Text))

Max Activating Token Index: 581

Text #17

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0401. Min Act: -0.0006

Data Index: 709444 (C4 (Web Text))

Max Activating Token Index: 758

Text #18

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0399. Min Act: -0.0006

Data Index: 967237 (C4 (Web Text))

Max Activating Token Index: 960

Text #19

Max Range: 0.0485. Min Range: -0.0485

Max Act: 0.0399. Min Act: -0.0006

Data Index: 158194 (C4 (Web Text))

Max Activating Token Index: 502