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

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

Neuron 5335 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9944. Min Range: -1.9944

Max Act: 1.9944. Min Act: -0.0000

Data Index: 1396597 (Python Code)

Max Activating Token Index: 884

Text #1

Max Range: 1.9944. Min Range: -1.9944

Max Act: 0.9079. Min Act: -0.0000

Data Index: 1559360 (Python Code)

Max Activating Token Index: 526

Text #2

Max Range: 1.9944. Min Range: -1.9944

Max Act: 0.8105. Min Act: -0.0000

Data Index: 1322871 (C4 (Web Text))

Max Activating Token Index: 679

Text #3

Max Range: 1.9944. Min Range: -1.9944

Max Act: 0.8404. Min Act: -0.0000

Data Index: 1445183 (Python Code)

Max Activating Token Index: 312

Text #4

Max Range: 1.9944. Min Range: -1.9944

Max Act: 0.7747. Min Act: -0.0000

Data Index: 483047 (C4 (Web Text))

Max Activating Token Index: 801

Text #5

Max Range: 1.9944. Min Range: -1.9944

Max Act: 0.8076. Min Act: -0.0000

Data Index: 1453900 (Python Code)

Max Activating Token Index: 724

Text #6

Max Range: 1.9944. Min Range: -1.9944

Max Act: 0.7556. Min Act: -0.0000

Data Index: 1605547 (Python Code)

Max Activating Token Index: 535

Text #7

Max Range: 1.9944. Min Range: -1.9944

Max Act: 0.7998. Min Act: -0.0000

Data Index: 1349579 (C4 (Web Text))

Max Activating Token Index: 490

Text #8

Max Range: 1.9944. Min Range: -1.9944

Max Act: 0.7708. Min Act: -0.0000

Data Index: 1434561 (Python Code)

Max Activating Token Index: 833

Text #9

Max Range: 1.9944. Min Range: -1.9944

Max Act: 0.6687. Min Act: -0.0000

Data Index: 1364174 (Python Code)

Max Activating Token Index: 934

Text #10

Max Range: 1.9944. Min Range: -1.9944

Max Act: 0.7334. Min Act: -0.0000

Data Index: 1446454 (Python Code)

Max Activating Token Index: 418

Text #11

Max Range: 1.9944. Min Range: -1.9944

Max Act: 0.7211. Min Act: -0.0000

Data Index: 1511464 (Python Code)

Max Activating Token Index: 778

Text #12

Max Range: 1.9944. Min Range: -1.9944

Max Act: 0.6889. Min Act: -0.0000

Data Index: 1404479 (Python Code)

Max Activating Token Index: 346

Text #13

Max Range: 1.9944. Min Range: -1.9944

Max Act: 0.7342. Min Act: -0.0000

Data Index: 1418535 (Python Code)

Max Activating Token Index: 270

Text #14

Max Range: 1.9944. Min Range: -1.9944

Max Act: 0.6630. Min Act: -0.0000

Data Index: 1533433 (Python Code)

Max Activating Token Index: 442

Text #15

Max Range: 1.9944. Min Range: -1.9944

Max Act: 0.7121. Min Act: -0.0000

Data Index: 1417321 (Python Code)

Max Activating Token Index: 769

Text #16

Max Range: 1.9944. Min Range: -1.9944

Max Act: 0.6758. Min Act: -0.0000

Data Index: 1543341 (Python Code)

Max Activating Token Index: 428

Text #17

Max Range: 1.9944. Min Range: -1.9944

Max Act: 0.6700. Min Act: -0.0000

Data Index: 1410024 (Python Code)

Max Activating Token Index: 346

Text #18

Max Range: 1.9944. Min Range: -1.9944

Max Act: 0.6861. Min Act: -0.0000

Data Index: 1630863 (Python Code)

Max Activating Token Index: 309

Text #19

Max Range: 1.9944. Min Range: -1.9944

Max Act: 0.6799. Min Act: -0.0000

Data Index: 1422264 (Python Code)

Max Activating Token Index: 79