Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2320 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.7863. Min Act: -0.0000

Data Index: 26433 (C4 (Web Text))

Max Activating Token Index: 477

Text #1

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.8025. Min Act: -0.0000

Data Index: 885989 (C4 (Web Text))

Max Activating Token Index: 79

Text #2

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.8634. Min Act: -0.0000

Data Index: 129855 (C4 (Web Text))

Max Activating Token Index: 338

Text #3

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.7733. Min Act: -0.0001

Data Index: 247346 (C4 (Web Text))

Max Activating Token Index: 806

Text #4

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.7681. Min Act: -0.0000

Data Index: 284656 (C4 (Web Text))

Max Activating Token Index: 224

Text #5

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.7157. Min Act: -0.0001

Data Index: 853996 (C4 (Web Text))

Max Activating Token Index: 429

Text #6

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.7374. Min Act: -0.0000

Data Index: 524892 (C4 (Web Text))

Max Activating Token Index: 645

Text #7

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.7000. Min Act: -0.0000

Data Index: 721295 (C4 (Web Text))

Max Activating Token Index: 640

Text #8

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.7001. Min Act: -0.0001

Data Index: 47251 (C4 (Web Text))

Max Activating Token Index: 560

Text #9

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.7175. Min Act: -0.0000

Data Index: 132612 (C4 (Web Text))

Max Activating Token Index: 383

Text #10

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.6807. Min Act: -0.0000

Data Index: 444212 (C4 (Web Text))

Max Activating Token Index: 791

Text #11

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.6785. Min Act: -0.0000

Data Index: 73310 (C4 (Web Text))

Max Activating Token Index: 460

Text #12

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.7260. Min Act: -0.0000

Data Index: 288333 (C4 (Web Text))

Max Activating Token Index: 383

Text #13

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.7299. Min Act: -0.0001

Data Index: 509889 (C4 (Web Text))

Max Activating Token Index: 552

Text #14

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.6861. Min Act: -0.0000

Data Index: 1256587 (C4 (Web Text))

Max Activating Token Index: 757

Text #15

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.6771. Min Act: -0.0000

Data Index: 602720 (C4 (Web Text))

Max Activating Token Index: 193

Text #16

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.6538. Min Act: -0.0000

Data Index: 903486 (C4 (Web Text))

Max Activating Token Index: 667

Text #17

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.6179. Min Act: -0.0001

Data Index: 859499 (C4 (Web Text))

Max Activating Token Index: 862

Text #18

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.5906. Min Act: -0.0001

Data Index: 1150197 (C4 (Web Text))

Max Activating Token Index: 309

Text #19

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.6314. Min Act: -0.0000

Data Index: 1019245 (C4 (Web Text))

Max Activating Token Index: 190