Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1300 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.7270. Min Range: -3.7270

Max Act: 3.5454. Min Act: -0.0000

Data Index: 285070 (C4 (Web Text))

Max Activating Token Index: 939

Text #1

Max Range: 3.7270. Min Range: -3.7270

Max Act: 3.2913. Min Act: -0.0000

Data Index: 835944 (C4 (Web Text))

Max Activating Token Index: 941

Text #2

Max Range: 3.7270. Min Range: -3.7270

Max Act: 3.7270. Min Act: -0.0000

Data Index: 823115 (C4 (Web Text))

Max Activating Token Index: 996

Text #3

Max Range: 3.7270. Min Range: -3.7270

Max Act: 3.0066. Min Act: -0.0000

Data Index: 551712 (C4 (Web Text))

Max Activating Token Index: 704

Text #4

Max Range: 3.7270. Min Range: -3.7270

Max Act: 2.6247. Min Act: -0.0000

Data Index: 428692 (C4 (Web Text))

Max Activating Token Index: 257

Text #5

Max Range: 3.7270. Min Range: -3.7270

Max Act: 3.3083. Min Act: -0.0000

Data Index: 1152696 (C4 (Web Text))

Max Activating Token Index: 858

Text #6

Max Range: 3.7270. Min Range: -3.7270

Max Act: 2.3226. Min Act: -0.0000

Data Index: 473488 (C4 (Web Text))

Max Activating Token Index: 500

Text #7

Max Range: 3.7270. Min Range: -3.7270

Max Act: 2.1957. Min Act: -0.0000

Data Index: 893535 (C4 (Web Text))

Max Activating Token Index: 416

Text #8

Max Range: 3.7270. Min Range: -3.7270

Max Act: 1.8409. Min Act: -0.0000

Data Index: 605416 (C4 (Web Text))

Max Activating Token Index: 319

Text #9

Max Range: 3.7270. Min Range: -3.7270

Max Act: 1.5823. Min Act: -0.0000

Data Index: 1021970 (C4 (Web Text))

Max Activating Token Index: 86

Text #10

Max Range: 3.7270. Min Range: -3.7270

Max Act: 1.5516. Min Act: -0.0000

Data Index: 552114 (C4 (Web Text))

Max Activating Token Index: 663

Text #11

Max Range: 3.7270. Min Range: -3.7270

Max Act: 1.3702. Min Act: -0.0000

Data Index: 845109 (C4 (Web Text))

Max Activating Token Index: 657

Text #12

Max Range: 3.7270. Min Range: -3.7270

Max Act: 1.2746. Min Act: -0.0000

Data Index: 273570 (C4 (Web Text))

Max Activating Token Index: 603

Text #13

Max Range: 3.7270. Min Range: -3.7270

Max Act: 1.0582. Min Act: -0.0000

Data Index: 133453 (C4 (Web Text))

Max Activating Token Index: 898

Text #14

Max Range: 3.7270. Min Range: -3.7270

Max Act: 1.0659. Min Act: -0.0000

Data Index: 447949 (C4 (Web Text))

Max Activating Token Index: 732

Text #15

Max Range: 3.7270. Min Range: -3.7270

Max Act: 1.0020. Min Act: -0.0000

Data Index: 813087 (C4 (Web Text))

Max Activating Token Index: 312

Text #16

Max Range: 3.7270. Min Range: -3.7270

Max Act: 1.2894. Min Act: -0.0000

Data Index: 378572 (C4 (Web Text))

Max Activating Token Index: 478

Text #17

Max Range: 3.7270. Min Range: -3.7270

Max Act: 1.2318. Min Act: -0.0000

Data Index: 1343746 (C4 (Web Text))

Max Activating Token Index: 951

Text #18

Max Range: 3.7270. Min Range: -3.7270

Max Act: 1.0505. Min Act: -0.0000

Data Index: 1039434 (C4 (Web Text))

Max Activating Token Index: 120

Text #19

Max Range: 3.7270. Min Range: -3.7270

Max Act: 0.9675. Min Act: -0.0000

Data Index: 119304 (C4 (Web Text))

Max Activating Token Index: 268