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

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

Neuron 247 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3449. Min Range: -0.3449

Max Act: 0.3449. Min Act: -0.0000

Data Index: 1320398 (C4 (Web Text))

Max Activating Token Index: 151

Text #1

Max Range: 0.3449. Min Range: -0.3449

Max Act: 0.3213. Min Act: -0.0001

Data Index: 1355016 (C4 (Web Text))

Max Activating Token Index: 947

Text #2

Max Range: 0.3449. Min Range: -0.3449

Max Act: 0.2929. Min Act: -0.0000

Data Index: 252471 (C4 (Web Text))

Max Activating Token Index: 57

Text #3

Max Range: 0.3449. Min Range: -0.3449

Max Act: 0.2763. Min Act: -0.0001

Data Index: 1131005 (C4 (Web Text))

Max Activating Token Index: 764

Text #4

Max Range: 0.3449. Min Range: -0.3449

Max Act: 0.2940. Min Act: -0.0001

Data Index: 1252590 (C4 (Web Text))

Max Activating Token Index: 902

Text #5

Max Range: 0.3449. Min Range: -0.3449

Max Act: 0.2817. Min Act: -0.0001

Data Index: 352536 (C4 (Web Text))

Max Activating Token Index: 232

Text #6

Max Range: 0.3449. Min Range: -0.3449

Max Act: 0.2904. Min Act: -0.0001

Data Index: 196391 (C4 (Web Text))

Max Activating Token Index: 95

Text #7

Max Range: 0.3449. Min Range: -0.3449

Max Act: 0.2770. Min Act: -0.0001

Data Index: 303493 (C4 (Web Text))

Max Activating Token Index: 372

Text #8

Max Range: 0.3449. Min Range: -0.3449

Max Act: 0.2723. Min Act: -0.0000

Data Index: 833598 (C4 (Web Text))

Max Activating Token Index: 769

Text #9

Max Range: 0.3449. Min Range: -0.3449

Max Act: 0.2683. Min Act: -0.0000

Data Index: 66880 (C4 (Web Text))

Max Activating Token Index: 420

Text #10

Max Range: 0.3449. Min Range: -0.3449

Max Act: 0.2773. Min Act: -0.0001

Data Index: 1110657 (C4 (Web Text))

Max Activating Token Index: 425

Text #11

Max Range: 0.3449. Min Range: -0.3449

Max Act: 0.2833. Min Act: -0.0000

Data Index: 1286382 (C4 (Web Text))

Max Activating Token Index: 667

Text #12

Max Range: 0.3449. Min Range: -0.3449

Max Act: 0.2833. Min Act: -0.0001

Data Index: 738905 (C4 (Web Text))

Max Activating Token Index: 972

Text #13

Max Range: 0.3449. Min Range: -0.3449

Max Act: 0.2989. Min Act: -0.0000

Data Index: 582860 (C4 (Web Text))

Max Activating Token Index: 113

Text #14

Max Range: 0.3449. Min Range: -0.3449

Max Act: 0.2599. Min Act: -0.0000

Data Index: 1098208 (C4 (Web Text))

Max Activating Token Index: 711

Text #15

Max Range: 0.3449. Min Range: -0.3449

Max Act: 0.2744. Min Act: -0.0000

Data Index: 724015 (C4 (Web Text))

Max Activating Token Index: 479

Text #16

Max Range: 0.3449. Min Range: -0.3449

Max Act: 0.2472. Min Act: -0.0000

Data Index: 117893 (C4 (Web Text))

Max Activating Token Index: 278

Text #17

Max Range: 0.3449. Min Range: -0.3449

Max Act: 0.2549. Min Act: -0.0000

Data Index: 2152 (C4 (Web Text))

Max Activating Token Index: 163

Text #18

Max Range: 0.3449. Min Range: -0.3449

Max Act: 0.2421. Min Act: -0.0001

Data Index: 763166 (C4 (Web Text))

Max Activating Token Index: 249

Text #19

Max Range: 0.3449. Min Range: -0.3449

Max Act: 0.2566. Min Act: -0.0001

Data Index: 834336 (C4 (Web Text))

Max Activating Token Index: 40