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

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

Neuron 5825 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.9402. Min Act: -0.0000

Data Index: 190865 (C4 (Web Text))

Max Activating Token Index: 753

Text #1

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.9210. Min Act: -0.0000

Data Index: 955671 (C4 (Web Text))

Max Activating Token Index: 343

Text #2

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.8481. Min Act: -0.0000

Data Index: 100901 (C4 (Web Text))

Max Activating Token Index: 548

Text #3

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.8123. Min Act: -0.0000

Data Index: 376880 (C4 (Web Text))

Max Activating Token Index: 601

Text #4

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.9165. Min Act: -0.0000

Data Index: 396326 (C4 (Web Text))

Max Activating Token Index: 155

Text #5

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.7608. Min Act: -0.0000

Data Index: 557310 (C4 (Web Text))

Max Activating Token Index: 51

Text #6

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.6210. Min Act: -0.0000

Data Index: 803831 (C4 (Web Text))

Max Activating Token Index: 258

Text #7

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.5876. Min Act: -0.0000

Data Index: 23830 (C4 (Web Text))

Max Activating Token Index: 651

Text #8

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.6426. Min Act: -0.0000

Data Index: 989136 (C4 (Web Text))

Max Activating Token Index: 122

Text #9

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.6409. Min Act: -0.0000

Data Index: 775115 (C4 (Web Text))

Max Activating Token Index: 604

Text #10

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.5944. Min Act: -0.0000

Data Index: 726304 (C4 (Web Text))

Max Activating Token Index: 571

Text #11

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.5755. Min Act: -0.0000

Data Index: 352310 (C4 (Web Text))

Max Activating Token Index: 113

Text #12

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.5688. Min Act: -0.0000

Data Index: 1131778 (C4 (Web Text))

Max Activating Token Index: 883

Text #13

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.5641. Min Act: -0.0000

Data Index: 166348 (C4 (Web Text))

Max Activating Token Index: 83

Text #14

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.5937. Min Act: -0.0000

Data Index: 1116435 (C4 (Web Text))

Max Activating Token Index: 175

Text #15

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.5655. Min Act: -0.0000

Data Index: 335927 (C4 (Web Text))

Max Activating Token Index: 121

Text #16

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.5687. Min Act: -0.0000

Data Index: 1234333 (C4 (Web Text))

Max Activating Token Index: 195

Text #17

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.5346. Min Act: -0.0000

Data Index: 657161 (C4 (Web Text))

Max Activating Token Index: 685

Text #18

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.5002. Min Act: -0.0000

Data Index: 1022323 (C4 (Web Text))

Max Activating Token Index: 713

Text #19

Max Range: 0.9402. Min Range: -0.9402

Max Act: 0.5368. Min Act: -0.0000

Data Index: 660193 (C4 (Web Text))

Max Activating Token Index: 482