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

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

Neuron 3544 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.3273. Min Act: -0.0000

Data Index: 439879 (C4 (Web Text))

Max Activating Token Index: 198

Text #1

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.2955. Min Act: -0.0000

Data Index: 885651 (C4 (Web Text))

Max Activating Token Index: 800

Text #2

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.3151. Min Act: -0.0000

Data Index: 437163 (C4 (Web Text))

Max Activating Token Index: 617

Text #3

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.2921. Min Act: -0.0000

Data Index: 54919 (C4 (Web Text))

Max Activating Token Index: 137

Text #4

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.2932. Min Act: -0.0000

Data Index: 946294 (C4 (Web Text))

Max Activating Token Index: 275

Text #5

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.2893. Min Act: -0.0000

Data Index: 843635 (C4 (Web Text))

Max Activating Token Index: 339

Text #6

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.2987. Min Act: -0.0000

Data Index: 1297461 (C4 (Web Text))

Max Activating Token Index: 432

Text #7

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.3020. Min Act: -0.0000

Data Index: 916140 (C4 (Web Text))

Max Activating Token Index: 339

Text #8

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.2919. Min Act: -0.0000

Data Index: 775762 (C4 (Web Text))

Max Activating Token Index: 315

Text #9

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.2887. Min Act: -0.0000

Data Index: 560291 (C4 (Web Text))

Max Activating Token Index: 444

Text #10

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.2881. Min Act: -0.0000

Data Index: 878586 (C4 (Web Text))

Max Activating Token Index: 549

Text #11

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.2695. Min Act: -0.0000

Data Index: 839677 (C4 (Web Text))

Max Activating Token Index: 338

Text #12

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.2751. Min Act: -0.0000

Data Index: 533520 (C4 (Web Text))

Max Activating Token Index: 728

Text #13

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.2643. Min Act: -0.0000

Data Index: 1203150 (C4 (Web Text))

Max Activating Token Index: 736

Text #14

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.2732. Min Act: -0.0000

Data Index: 293788 (C4 (Web Text))

Max Activating Token Index: 408

Text #15

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.2842. Min Act: -0.0000

Data Index: 245619 (C4 (Web Text))

Max Activating Token Index: 630

Text #16

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.2649. Min Act: -0.0000

Data Index: 850673 (C4 (Web Text))

Max Activating Token Index: 342

Text #17

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.2726. Min Act: -0.0000

Data Index: 1320977 (C4 (Web Text))

Max Activating Token Index: 980

Text #18

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.2725. Min Act: -0.0000

Data Index: 170745 (C4 (Web Text))

Max Activating Token Index: 300

Text #19

Max Range: 0.3273. Min Range: -0.3273

Max Act: 0.2632. Min Act: -0.0000

Data Index: 603497 (C4 (Web Text))

Max Activating Token Index: 266