Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 249 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8485. Min Range: -0.8485

Max Act: 0.8485. Min Act: -0.0000

Data Index: 1073236 (C4 (Web Text))

Max Activating Token Index: 803

Text #1

Max Range: 0.8485. Min Range: -0.8485

Max Act: 0.8232. Min Act: -0.0000

Data Index: 461404 (C4 (Web Text))

Max Activating Token Index: 1002

Text #2

Max Range: 0.8485. Min Range: -0.8485

Max Act: 0.7056. Min Act: -0.0000

Data Index: 257866 (C4 (Web Text))

Max Activating Token Index: 334

Text #3

Max Range: 0.8485. Min Range: -0.8485

Max Act: 0.7484. Min Act: -0.0000

Data Index: 28890 (C4 (Web Text))

Max Activating Token Index: 220

Text #4

Max Range: 0.8485. Min Range: -0.8485

Max Act: 0.7676. Min Act: -0.0000

Data Index: 454058 (C4 (Web Text))

Max Activating Token Index: 209

Text #5

Max Range: 0.8485. Min Range: -0.8485

Max Act: 0.7056. Min Act: -0.0000

Data Index: 171662 (C4 (Web Text))

Max Activating Token Index: 387

Text #6

Max Range: 0.8485. Min Range: -0.8485

Max Act: 0.7158. Min Act: -0.0000

Data Index: 1130787 (C4 (Web Text))

Max Activating Token Index: 726

Text #7

Max Range: 0.8485. Min Range: -0.8485

Max Act: 0.6855. Min Act: -0.0000

Data Index: 528227 (C4 (Web Text))

Max Activating Token Index: 823

Text #8

Max Range: 0.8485. Min Range: -0.8485

Max Act: 0.6771. Min Act: -0.0000

Data Index: 905473 (C4 (Web Text))

Max Activating Token Index: 997

Text #9

Max Range: 0.8485. Min Range: -0.8485

Max Act: 0.6721. Min Act: -0.0000

Data Index: 868227 (C4 (Web Text))

Max Activating Token Index: 107

Text #10

Max Range: 0.8485. Min Range: -0.8485

Max Act: 0.6735. Min Act: -0.0000

Data Index: 1351289 (C4 (Web Text))

Max Activating Token Index: 67

Text #11

Max Range: 0.8485. Min Range: -0.8485

Max Act: 0.6526. Min Act: -0.0000

Data Index: 721533 (C4 (Web Text))

Max Activating Token Index: 272

Text #12

Max Range: 0.8485. Min Range: -0.8485

Max Act: 0.6269. Min Act: -0.0000

Data Index: 1151306 (C4 (Web Text))

Max Activating Token Index: 684

Text #13

Max Range: 0.8485. Min Range: -0.8485

Max Act: 0.6185. Min Act: -0.0000

Data Index: 521586 (C4 (Web Text))

Max Activating Token Index: 81

Text #14

Max Range: 0.8485. Min Range: -0.8485

Max Act: 0.6239. Min Act: -0.0000

Data Index: 827706 (C4 (Web Text))

Max Activating Token Index: 325

Text #15

Max Range: 0.8485. Min Range: -0.8485

Max Act: 0.6202. Min Act: -0.0000

Data Index: 234211 (C4 (Web Text))

Max Activating Token Index: 637

Text #16

Max Range: 0.8485. Min Range: -0.8485

Max Act: 0.6348. Min Act: -0.0000

Data Index: 1049201 (C4 (Web Text))

Max Activating Token Index: 297

Text #17

Max Range: 0.8485. Min Range: -0.8485

Max Act: 0.6507. Min Act: -0.0000

Data Index: 1032931 (C4 (Web Text))

Max Activating Token Index: 896

Text #18

Max Range: 0.8485. Min Range: -0.8485

Max Act: 0.6255. Min Act: -0.0000

Data Index: 1276139 (C4 (Web Text))

Max Activating Token Index: 733

Text #19

Max Range: 0.8485. Min Range: -0.8485

Max Act: 0.5977. Min Act: -0.0000

Data Index: 304091 (C4 (Web Text))

Max Activating Token Index: 453