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

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

Neuron 1174 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9186. Min Range: -1.9186

Max Act: 1.9186. Min Act: -0.0001

Data Index: 929165 (C4 (Web Text))

Max Activating Token Index: 564

Text #1

Max Range: 1.9186. Min Range: -1.9186

Max Act: 1.5557. Min Act: -0.0001

Data Index: 686612 (C4 (Web Text))

Max Activating Token Index: 827

Text #2

Max Range: 1.9186. Min Range: -1.9186

Max Act: 1.5346. Min Act: -0.0001

Data Index: 443131 (C4 (Web Text))

Max Activating Token Index: 6

Text #3

Max Range: 1.9186. Min Range: -1.9186

Max Act: 1.3757. Min Act: -0.0001

Data Index: 520916 (C4 (Web Text))

Max Activating Token Index: 675

Text #4

Max Range: 1.9186. Min Range: -1.9186

Max Act: 1.4380. Min Act: -0.0001

Data Index: 291413 (C4 (Web Text))

Max Activating Token Index: 716

Text #5

Max Range: 1.9186. Min Range: -1.9186

Max Act: 1.5886. Min Act: -0.0001

Data Index: 1060587 (C4 (Web Text))

Max Activating Token Index: 836

Text #6

Max Range: 1.9186. Min Range: -1.9186

Max Act: 1.3025. Min Act: -0.0001

Data Index: 1089854 (C4 (Web Text))

Max Activating Token Index: 857

Text #7

Max Range: 1.9186. Min Range: -1.9186

Max Act: 1.3214. Min Act: -0.0001

Data Index: 847382 (C4 (Web Text))

Max Activating Token Index: 683

Text #8

Max Range: 1.9186. Min Range: -1.9186

Max Act: 1.2765. Min Act: -0.0001

Data Index: 1048778 (C4 (Web Text))

Max Activating Token Index: 366

Text #9

Max Range: 1.9186. Min Range: -1.9186

Max Act: 1.3291. Min Act: -0.0001

Data Index: 84759 (C4 (Web Text))

Max Activating Token Index: 636

Text #10

Max Range: 1.9186. Min Range: -1.9186

Max Act: 1.3110. Min Act: -0.0001

Data Index: 836255 (C4 (Web Text))

Max Activating Token Index: 911

Text #11

Max Range: 1.9186. Min Range: -1.9186

Max Act: 1.2060. Min Act: -0.0001

Data Index: 412165 (C4 (Web Text))

Max Activating Token Index: 394

Text #12

Max Range: 1.9186. Min Range: -1.9186

Max Act: 1.2052. Min Act: -0.0001

Data Index: 568089 (C4 (Web Text))

Max Activating Token Index: 503

Text #13

Max Range: 1.9186. Min Range: -1.9186

Max Act: 1.2162. Min Act: -0.0001

Data Index: 505765 (C4 (Web Text))

Max Activating Token Index: 192

Text #14

Max Range: 1.9186. Min Range: -1.9186

Max Act: 1.2371. Min Act: -0.0001

Data Index: 1044399 (C4 (Web Text))

Max Activating Token Index: 334

Text #15

Max Range: 1.9186. Min Range: -1.9186

Max Act: 1.1591. Min Act: -0.0001

Data Index: 238514 (C4 (Web Text))

Max Activating Token Index: 741

Text #16

Max Range: 1.9186. Min Range: -1.9186

Max Act: 1.1377. Min Act: -0.0001

Data Index: 176097 (C4 (Web Text))

Max Activating Token Index: 566

Text #17

Max Range: 1.9186. Min Range: -1.9186

Max Act: 1.1617. Min Act: -0.0001

Data Index: 108135 (C4 (Web Text))

Max Activating Token Index: 249

Text #18

Max Range: 1.9186. Min Range: -1.9186

Max Act: 1.1499. Min Act: -0.0001

Data Index: 498486 (C4 (Web Text))

Max Activating Token Index: 851

Text #19

Max Range: 1.9186. Min Range: -1.9186

Max Act: 1.2561. Min Act: -0.0001

Data Index: 923372 (C4 (Web Text))

Max Activating Token Index: 709