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

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

Neuron 829 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.3307. Min Act: -0.0003

Data Index: 139393 (C4 (Web Text))

Max Activating Token Index: 589

Text #1

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.3190. Min Act: -0.0003

Data Index: 789363 (C4 (Web Text))

Max Activating Token Index: 520

Text #2

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2985. Min Act: -0.0003

Data Index: 1040280 (C4 (Web Text))

Max Activating Token Index: 371

Text #3

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2808. Min Act: -0.0004

Data Index: 340075 (C4 (Web Text))

Max Activating Token Index: 183

Text #4

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2863. Min Act: -0.0004

Data Index: 284924 (C4 (Web Text))

Max Activating Token Index: 242

Text #5

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2956. Min Act: -0.0003

Data Index: 807542 (C4 (Web Text))

Max Activating Token Index: 887

Text #6

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2931. Min Act: -0.0004

Data Index: 345418 (C4 (Web Text))

Max Activating Token Index: 39

Text #7

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2734. Min Act: -0.0003

Data Index: 407182 (C4 (Web Text))

Max Activating Token Index: 742

Text #8

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2849. Min Act: -0.0003

Data Index: 999176 (C4 (Web Text))

Max Activating Token Index: 431

Text #9

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2829. Min Act: -0.0004

Data Index: 340006 (C4 (Web Text))

Max Activating Token Index: 679

Text #10

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2757. Min Act: -0.0003

Data Index: 661879 (C4 (Web Text))

Max Activating Token Index: 197

Text #11

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2754. Min Act: -0.0003

Data Index: 545730 (C4 (Web Text))

Max Activating Token Index: 453

Text #12

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2830. Min Act: -0.0004

Data Index: 390746 (C4 (Web Text))

Max Activating Token Index: 827

Text #13

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2638. Min Act: -0.0003

Data Index: 586303 (C4 (Web Text))

Max Activating Token Index: 83

Text #14

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2617. Min Act: -0.0003

Data Index: 486001 (C4 (Web Text))

Max Activating Token Index: 1012

Text #15

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2783. Min Act: -0.0003

Data Index: 169072 (C4 (Web Text))

Max Activating Token Index: 352

Text #16

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2457. Min Act: -0.0003

Data Index: 1296693 (C4 (Web Text))

Max Activating Token Index: 504

Text #17

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2371. Min Act: -0.0003

Data Index: 665347 (C4 (Web Text))

Max Activating Token Index: 903

Text #18

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2602. Min Act: -0.0003

Data Index: 390231 (C4 (Web Text))

Max Activating Token Index: 506

Text #19

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2632. Min Act: -0.0003

Data Index: 691147 (C4 (Web Text))

Max Activating Token Index: 506