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

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

Neuron 538 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5877. Min Range: -4.5877

Max Act: 4.5704. Min Act: -0.0000

Data Index: 306215 (C4 (Web Text))

Max Activating Token Index: 842

Text #1

Max Range: 4.5877. Min Range: -4.5877

Max Act: 4.5877. Min Act: -0.0000

Data Index: 341311 (C4 (Web Text))

Max Activating Token Index: 335

Text #2

Max Range: 4.5877. Min Range: -4.5877

Max Act: 4.1827. Min Act: -0.0000

Data Index: 305910 (C4 (Web Text))

Max Activating Token Index: 838

Text #3

Max Range: 4.5877. Min Range: -4.5877

Max Act: 4.2388. Min Act: 0.0000

Data Index: 857175 (C4 (Web Text))

Max Activating Token Index: 400

Text #4

Max Range: 4.5877. Min Range: -4.5877

Max Act: 4.0851. Min Act: 0.0000

Data Index: 1244929 (C4 (Web Text))

Max Activating Token Index: 224

Text #5

Max Range: 4.5877. Min Range: -4.5877

Max Act: 4.0193. Min Act: 0.0000

Data Index: 417314 (C4 (Web Text))

Max Activating Token Index: 724

Text #6

Max Range: 4.5877. Min Range: -4.5877

Max Act: 3.5175. Min Act: 0.0000

Data Index: 387519 (C4 (Web Text))

Max Activating Token Index: 104

Text #7

Max Range: 4.5877. Min Range: -4.5877

Max Act: 3.6130. Min Act: 0.0000

Data Index: 554373 (C4 (Web Text))

Max Activating Token Index: 450

Text #8

Max Range: 4.5877. Min Range: -4.5877

Max Act: 3.7475. Min Act: -0.0000

Data Index: 1225586 (C4 (Web Text))

Max Activating Token Index: 321

Text #9

Max Range: 4.5877. Min Range: -4.5877

Max Act: 3.7490. Min Act: -0.0000

Data Index: 728431 (C4 (Web Text))

Max Activating Token Index: 388

Text #10

Max Range: 4.5877. Min Range: -4.5877

Max Act: 3.7168. Min Act: -0.0000

Data Index: 414941 (C4 (Web Text))

Max Activating Token Index: 958

Text #11

Max Range: 4.5877. Min Range: -4.5877

Max Act: 3.3225. Min Act: -0.0000

Data Index: 743060 (C4 (Web Text))

Max Activating Token Index: 886

Text #12

Max Range: 4.5877. Min Range: -4.5877

Max Act: 3.5471. Min Act: -0.0000

Data Index: 692794 (C4 (Web Text))

Max Activating Token Index: 815

Text #13

Max Range: 4.5877. Min Range: -4.5877

Max Act: 3.4097. Min Act: -0.0000

Data Index: 1045422 (C4 (Web Text))

Max Activating Token Index: 165

Text #14

Max Range: 4.5877. Min Range: -4.5877

Max Act: 3.2690. Min Act: -0.0000

Data Index: 637982 (C4 (Web Text))

Max Activating Token Index: 542

Text #15

Max Range: 4.5877. Min Range: -4.5877

Max Act: 3.0594. Min Act: -0.0000

Data Index: 379110 (C4 (Web Text))

Max Activating Token Index: 810

Text #16

Max Range: 4.5877. Min Range: -4.5877

Max Act: 3.5160. Min Act: -0.0000

Data Index: 207614 (C4 (Web Text))

Max Activating Token Index: 250

Text #17

Max Range: 4.5877. Min Range: -4.5877

Max Act: 2.8584. Min Act: -0.0000

Data Index: 751447 (C4 (Web Text))

Max Activating Token Index: 777

Text #18

Max Range: 4.5877. Min Range: -4.5877

Max Act: 3.1985. Min Act: 0.0000

Data Index: 132120 (C4 (Web Text))

Max Activating Token Index: 94

Text #19

Max Range: 4.5877. Min Range: -4.5877

Max Act: 3.1693. Min Act: -0.0000

Data Index: 775042 (C4 (Web Text))

Max Activating Token Index: 422