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

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

Neuron 4539 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: 1.0308. Min Range: -1.0308

Max Act: 1.0308. Min Act: -0.0000

Data Index: 365517 (C4 (Web Text))

Max Activating Token Index: 499

Text #1

Max Range: 1.0308. Min Range: -1.0308

Max Act: 0.9413. Min Act: -0.0000

Data Index: 381773 (C4 (Web Text))

Max Activating Token Index: 58

Text #2

Max Range: 1.0308. Min Range: -1.0308

Max Act: 1.0249. Min Act: -0.0000

Data Index: 33491 (C4 (Web Text))

Max Activating Token Index: 386

Text #3

Max Range: 1.0308. Min Range: -1.0308

Max Act: 0.9683. Min Act: -0.0000

Data Index: 512972 (C4 (Web Text))

Max Activating Token Index: 512

Text #4

Max Range: 1.0308. Min Range: -1.0308

Max Act: 0.9316. Min Act: -0.0000

Data Index: 405120 (C4 (Web Text))

Max Activating Token Index: 89

Text #5

Max Range: 1.0308. Min Range: -1.0308

Max Act: 0.9617. Min Act: -0.0000

Data Index: 1026222 (C4 (Web Text))

Max Activating Token Index: 87

Text #6

Max Range: 1.0308. Min Range: -1.0308

Max Act: 0.8385. Min Act: -0.0000

Data Index: 444565 (C4 (Web Text))

Max Activating Token Index: 50

Text #7

Max Range: 1.0308. Min Range: -1.0308

Max Act: 0.7918. Min Act: -0.0000

Data Index: 43515 (C4 (Web Text))

Max Activating Token Index: 755

Text #8

Max Range: 1.0308. Min Range: -1.0308

Max Act: 0.8577. Min Act: -0.0000

Data Index: 879738 (C4 (Web Text))

Max Activating Token Index: 200

Text #9

Max Range: 1.0308. Min Range: -1.0308

Max Act: 0.9046. Min Act: -0.0000

Data Index: 137470 (C4 (Web Text))

Max Activating Token Index: 882

Text #10

Max Range: 1.0308. Min Range: -1.0308

Max Act: 0.7952. Min Act: -0.0000

Data Index: 873794 (C4 (Web Text))

Max Activating Token Index: 89

Text #11

Max Range: 1.0308. Min Range: -1.0308

Max Act: 0.8381. Min Act: -0.0000

Data Index: 357765 (C4 (Web Text))

Max Activating Token Index: 571

Text #12

Max Range: 1.0308. Min Range: -1.0308

Max Act: 0.8557. Min Act: -0.0000

Data Index: 1206608 (C4 (Web Text))

Max Activating Token Index: 276

Text #13

Max Range: 1.0308. Min Range: -1.0308

Max Act: 0.8200. Min Act: -0.0000

Data Index: 735181 (C4 (Web Text))

Max Activating Token Index: 707

Text #14

Max Range: 1.0308. Min Range: -1.0308

Max Act: 0.8328. Min Act: -0.0000

Data Index: 172163 (C4 (Web Text))

Max Activating Token Index: 500

Text #15

Max Range: 1.0308. Min Range: -1.0308

Max Act: 0.9305. Min Act: -0.0000

Data Index: 306534 (C4 (Web Text))

Max Activating Token Index: 319

Text #16

Max Range: 1.0308. Min Range: -1.0308

Max Act: 0.8167. Min Act: -0.0000

Data Index: 516109 (C4 (Web Text))

Max Activating Token Index: 461

Text #17

Max Range: 1.0308. Min Range: -1.0308

Max Act: 0.8376. Min Act: -0.0000

Data Index: 4574 (C4 (Web Text))

Max Activating Token Index: 196

Text #18

Max Range: 1.0308. Min Range: -1.0308

Max Act: 0.7591. Min Act: -0.0000

Data Index: 918416 (C4 (Web Text))

Max Activating Token Index: 154

Text #19

Max Range: 1.0308. Min Range: -1.0308

Max Act: 0.8080. Min Act: -0.0000

Data Index: 1181574 (C4 (Web Text))

Max Activating Token Index: 90