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

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

Neuron 4057 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9314. Min Range: -0.9314

Max Act: 0.9107. Min Act: -0.0002

Data Index: 1494227 (Python Code)

Max Activating Token Index: 387

Text #1

Max Range: 0.9314. Min Range: -0.9314

Max Act: 0.9314. Min Act: -0.0002

Data Index: 814980 (C4 (Web Text))

Max Activating Token Index: 765

Text #2

Max Range: 0.9314. Min Range: -0.9314

Max Act: 0.8387. Min Act: -0.0002

Data Index: 1400294 (Python Code)

Max Activating Token Index: 875

Text #3

Max Range: 0.9314. Min Range: -0.9314

Max Act: 0.8430. Min Act: -0.0002

Data Index: 1379944 (Python Code)

Max Activating Token Index: 689

Text #4

Max Range: 0.9314. Min Range: -0.9314

Max Act: 0.8064. Min Act: -0.0002

Data Index: 1417521 (Python Code)

Max Activating Token Index: 715

Text #5

Max Range: 0.9314. Min Range: -0.9314

Max Act: 0.8293. Min Act: -0.0002

Data Index: 1474729 (Python Code)

Max Activating Token Index: 188

Text #6

Max Range: 0.9314. Min Range: -0.9314

Max Act: 0.7230. Min Act: -0.0002

Data Index: 1293429 (C4 (Web Text))

Max Activating Token Index: 125

Text #7

Max Range: 0.9314. Min Range: -0.9314

Max Act: 0.7129. Min Act: -0.0002

Data Index: 1074368 (C4 (Web Text))

Max Activating Token Index: 703

Text #8

Max Range: 0.9314. Min Range: -0.9314

Max Act: 0.7324. Min Act: -0.0002

Data Index: 1655584 (Python Code)

Max Activating Token Index: 733

Text #9

Max Range: 0.9314. Min Range: -0.9314

Max Act: 0.7281. Min Act: -0.0002

Data Index: 1430669 (Python Code)

Max Activating Token Index: 569

Text #10

Max Range: 0.9314. Min Range: -0.9314

Max Act: 0.7151. Min Act: -0.0002

Data Index: 824449 (C4 (Web Text))

Max Activating Token Index: 97

Text #11

Max Range: 0.9314. Min Range: -0.9314

Max Act: 0.7134. Min Act: -0.0002

Data Index: 1528383 (Python Code)

Max Activating Token Index: 246

Text #12

Max Range: 0.9314. Min Range: -0.9314

Max Act: 0.6889. Min Act: -0.0002

Data Index: 1312572 (C4 (Web Text))

Max Activating Token Index: 192

Text #13

Max Range: 0.9314. Min Range: -0.9314

Max Act: 0.6974. Min Act: -0.0002

Data Index: 1107323 (C4 (Web Text))

Max Activating Token Index: 414

Text #14

Max Range: 0.9314. Min Range: -0.9314

Max Act: 0.6983. Min Act: -0.0002

Data Index: 232545 (C4 (Web Text))

Max Activating Token Index: 485

Text #15

Max Range: 0.9314. Min Range: -0.9314

Max Act: 0.6903. Min Act: -0.0002

Data Index: 1476009 (Python Code)

Max Activating Token Index: 157

Text #16

Max Range: 0.9314. Min Range: -0.9314

Max Act: 0.6856. Min Act: -0.0002

Data Index: 449814 (C4 (Web Text))

Max Activating Token Index: 751

Text #17

Max Range: 0.9314. Min Range: -0.9314

Max Act: 0.6633. Min Act: -0.0002

Data Index: 361579 (C4 (Web Text))

Max Activating Token Index: 654

Text #18

Max Range: 0.9314. Min Range: -0.9314

Max Act: 0.6627. Min Act: -0.0002

Data Index: 198280 (C4 (Web Text))

Max Activating Token Index: 361

Text #19

Max Range: 0.9314. Min Range: -0.9314

Max Act: 0.6496. Min Act: -0.0002

Data Index: 1628221 (Python Code)

Max Activating Token Index: 326