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

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

Neuron 104 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: 1.4695. Min Range: -1.4695

Max Act: 1.4695. Min Act: -0.0000

Data Index: 1454937 (Python Code)

Max Activating Token Index: 45

Text #1

Max Range: 1.4695. Min Range: -1.4695

Max Act: 1.2448. Min Act: -0.0000

Data Index: 1550594 (Python Code)

Max Activating Token Index: 556

Text #2

Max Range: 1.4695. Min Range: -1.4695

Max Act: 1.2044. Min Act: -0.0000

Data Index: 1393474 (Python Code)

Max Activating Token Index: 558

Text #3

Max Range: 1.4695. Min Range: -1.4695

Max Act: 1.1179. Min Act: -0.0000

Data Index: 1604707 (Python Code)

Max Activating Token Index: 397

Text #4

Max Range: 1.4695. Min Range: -1.4695

Max Act: 1.0111. Min Act: -0.0000

Data Index: 1625441 (Python Code)

Max Activating Token Index: 193

Text #5

Max Range: 1.4695. Min Range: -1.4695

Max Act: 1.0165. Min Act: -0.0000

Data Index: 1419928 (Python Code)

Max Activating Token Index: 467

Text #6

Max Range: 1.4695. Min Range: -1.4695

Max Act: 0.9781. Min Act: -0.0000

Data Index: 1472570 (Python Code)

Max Activating Token Index: 395

Text #7

Max Range: 1.4695. Min Range: -1.4695

Max Act: 0.9321. Min Act: -0.0000

Data Index: 1471837 (Python Code)

Max Activating Token Index: 143

Text #8

Max Range: 1.4695. Min Range: -1.4695

Max Act: 0.9672. Min Act: -0.0000

Data Index: 1631446 (Python Code)

Max Activating Token Index: 496

Text #9

Max Range: 1.4695. Min Range: -1.4695

Max Act: 0.9655. Min Act: -0.0000

Data Index: 1503581 (Python Code)

Max Activating Token Index: 95

Text #10

Max Range: 1.4695. Min Range: -1.4695

Max Act: 0.9124. Min Act: -0.0000

Data Index: 1461153 (Python Code)

Max Activating Token Index: 469

Text #11

Max Range: 1.4695. Min Range: -1.4695

Max Act: 0.8814. Min Act: -0.0000

Data Index: 1365540 (Python Code)

Max Activating Token Index: 235

Text #12

Max Range: 1.4695. Min Range: -1.4695

Max Act: 0.8591. Min Act: -0.0000

Data Index: 1504216 (Python Code)

Max Activating Token Index: 871

Text #13

Max Range: 1.4695. Min Range: -1.4695

Max Act: 0.9075. Min Act: -0.0000

Data Index: 1500794 (Python Code)

Max Activating Token Index: 448

Text #14

Max Range: 1.4695. Min Range: -1.4695

Max Act: 0.7902. Min Act: -0.0000

Data Index: 1397183 (Python Code)

Max Activating Token Index: 579

Text #15

Max Range: 1.4695. Min Range: -1.4695

Max Act: 0.8962. Min Act: -0.0000

Data Index: 1451774 (Python Code)

Max Activating Token Index: 925

Text #16

Max Range: 1.4695. Min Range: -1.4695

Max Act: 0.9168. Min Act: -0.0000

Data Index: 1423526 (Python Code)

Max Activating Token Index: 269

Text #17

Max Range: 1.4695. Min Range: -1.4695

Max Act: 0.8634. Min Act: -0.0000

Data Index: 1402458 (Python Code)

Max Activating Token Index: 274

Text #18

Max Range: 1.4695. Min Range: -1.4695

Max Act: 0.8813. Min Act: -0.0000

Data Index: 1525154 (Python Code)

Max Activating Token Index: 841

Text #19

Max Range: 1.4695. Min Range: -1.4695

Max Act: 0.8526. Min Act: -0.0000

Data Index: 1471850 (Python Code)

Max Activating Token Index: 510