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

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

Neuron 4081 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: 1.3419. Min Range: -1.3419

Max Act: 1.3419. Min Act: -0.0000

Data Index: 1116479 (C4 (Web Text))

Max Activating Token Index: 946

Text #1

Max Range: 1.3419. Min Range: -1.3419

Max Act: 1.1166. Min Act: -0.0000

Data Index: 750172 (C4 (Web Text))

Max Activating Token Index: 287

Text #2

Max Range: 1.3419. Min Range: -1.3419

Max Act: 1.1188. Min Act: -0.0000

Data Index: 516026 (C4 (Web Text))

Max Activating Token Index: 933

Text #3

Max Range: 1.3419. Min Range: -1.3419

Max Act: 0.9290. Min Act: -0.0000

Data Index: 1225810 (C4 (Web Text))

Max Activating Token Index: 718

Text #4

Max Range: 1.3419. Min Range: -1.3419

Max Act: 0.7774. Min Act: -0.0000

Data Index: 1586927 (Python Code)

Max Activating Token Index: 299

Text #5

Max Range: 1.3419. Min Range: -1.3419

Max Act: 0.9236. Min Act: -0.0000

Data Index: 720787 (C4 (Web Text))

Max Activating Token Index: 769

Text #6

Max Range: 1.3419. Min Range: -1.3419

Max Act: 0.9142. Min Act: -0.0000

Data Index: 1609578 (Python Code)

Max Activating Token Index: 316

Text #7

Max Range: 1.3419. Min Range: -1.3419

Max Act: 0.9487. Min Act: 0.0000

Data Index: 634499 (C4 (Web Text))

Max Activating Token Index: 41

Text #8

Max Range: 1.3419. Min Range: -1.3419

Max Act: 0.8525. Min Act: -0.0000

Data Index: 686141 (C4 (Web Text))

Max Activating Token Index: 581

Text #9

Max Range: 1.3419. Min Range: -1.3419

Max Act: 0.8682. Min Act: -0.0000

Data Index: 416940 (C4 (Web Text))

Max Activating Token Index: 24

Text #10

Max Range: 1.3419. Min Range: -1.3419

Max Act: 0.8456. Min Act: -0.0000

Data Index: 1371426 (Python Code)

Max Activating Token Index: 311

Text #11

Max Range: 1.3419. Min Range: -1.3419

Max Act: 0.8267. Min Act: -0.0000

Data Index: 1028598 (C4 (Web Text))

Max Activating Token Index: 214

Text #12

Max Range: 1.3419. Min Range: -1.3419

Max Act: 0.7999. Min Act: -0.0000

Data Index: 396962 (C4 (Web Text))

Max Activating Token Index: 78

Text #13

Max Range: 1.3419. Min Range: -1.3419

Max Act: 0.7799. Min Act: -0.0000

Data Index: 876327 (C4 (Web Text))

Max Activating Token Index: 781

Text #14

Max Range: 1.3419. Min Range: -1.3419

Max Act: 0.8119. Min Act: -0.0000

Data Index: 1588530 (Python Code)

Max Activating Token Index: 658

Text #15

Max Range: 1.3419. Min Range: -1.3419

Max Act: 0.7927. Min Act: -0.0000

Data Index: 978134 (C4 (Web Text))

Max Activating Token Index: 588

Text #16

Max Range: 1.3419. Min Range: -1.3419

Max Act: 0.7780. Min Act: -0.0000

Data Index: 612172 (C4 (Web Text))

Max Activating Token Index: 81

Text #17

Max Range: 1.3419. Min Range: -1.3419

Max Act: 0.7718. Min Act: -0.0000

Data Index: 1224162 (C4 (Web Text))

Max Activating Token Index: 56

Text #18

Max Range: 1.3419. Min Range: -1.3419

Max Act: 0.7706. Min Act: -0.0000

Data Index: 1435883 (Python Code)

Max Activating Token Index: 237

Text #19

Max Range: 1.3419. Min Range: -1.3419

Max Act: 0.7366. Min Act: -0.0000

Data Index: 463588 (C4 (Web Text))

Max Activating Token Index: 31