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

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

Neuron 4284 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 2.0368. Min Range: -2.0368

Max Act: 2.0368. Min Act: -0.0002

Data Index: 291558 (C4 (Web Text))

Max Activating Token Index: 1011

Text #1

Max Range: 2.0368. Min Range: -2.0368

Max Act: 2.0187. Min Act: -0.0002

Data Index: 987674 (C4 (Web Text))

Max Activating Token Index: 435

Text #2

Max Range: 2.0368. Min Range: -2.0368

Max Act: 1.9694. Min Act: -0.0002

Data Index: 1173356 (C4 (Web Text))

Max Activating Token Index: 974

Text #3

Max Range: 2.0368. Min Range: -2.0368

Max Act: 1.9212. Min Act: -0.0002

Data Index: 544904 (C4 (Web Text))

Max Activating Token Index: 873

Text #4

Max Range: 2.0368. Min Range: -2.0368

Max Act: 1.9287. Min Act: -0.0002

Data Index: 487523 (C4 (Web Text))

Max Activating Token Index: 511

Text #5

Max Range: 2.0368. Min Range: -2.0368

Max Act: 1.9049. Min Act: -0.0002

Data Index: 577643 (C4 (Web Text))

Max Activating Token Index: 831

Text #6

Max Range: 2.0368. Min Range: -2.0368

Max Act: 1.8512. Min Act: -0.0002

Data Index: 870636 (C4 (Web Text))

Max Activating Token Index: 811

Text #7

Max Range: 2.0368. Min Range: -2.0368

Max Act: 1.8388. Min Act: -0.0002

Data Index: 1240877 (C4 (Web Text))

Max Activating Token Index: 36

Text #8

Max Range: 2.0368. Min Range: -2.0368

Max Act: 1.8569. Min Act: -0.0002

Data Index: 1178534 (C4 (Web Text))

Max Activating Token Index: 275

Text #9

Max Range: 2.0368. Min Range: -2.0368

Max Act: 1.8145. Min Act: -0.0002

Data Index: 463897 (C4 (Web Text))

Max Activating Token Index: 640

Text #10

Max Range: 2.0368. Min Range: -2.0368

Max Act: 1.7711. Min Act: -0.0002

Data Index: 175022 (C4 (Web Text))

Max Activating Token Index: 402

Text #11

Max Range: 2.0368. Min Range: -2.0368

Max Act: 1.8075. Min Act: -0.0002

Data Index: 515582 (C4 (Web Text))

Max Activating Token Index: 132

Text #12

Max Range: 2.0368. Min Range: -2.0368

Max Act: 1.8252. Min Act: -0.0002

Data Index: 618580 (C4 (Web Text))

Max Activating Token Index: 677

Text #13

Max Range: 2.0368. Min Range: -2.0368

Max Act: 1.8636. Min Act: -0.0002

Data Index: 635928 (C4 (Web Text))

Max Activating Token Index: 392

Text #14

Max Range: 2.0368. Min Range: -2.0368

Max Act: 1.7688. Min Act: -0.0002

Data Index: 12465 (C4 (Web Text))

Max Activating Token Index: 1003

Text #15

Max Range: 2.0368. Min Range: -2.0368

Max Act: 1.7736. Min Act: -0.0002

Data Index: 634391 (C4 (Web Text))

Max Activating Token Index: 718

Text #16

Max Range: 2.0368. Min Range: -2.0368

Max Act: 1.7792. Min Act: -0.0002

Data Index: 1117369 (C4 (Web Text))

Max Activating Token Index: 683

Text #17

Max Range: 2.0368. Min Range: -2.0368

Max Act: 1.8107. Min Act: -0.0002

Data Index: 1531 (C4 (Web Text))

Max Activating Token Index: 450

Text #18

Max Range: 2.0368. Min Range: -2.0368

Max Act: 1.7798. Min Act: -0.0002

Data Index: 515274 (C4 (Web Text))

Max Activating Token Index: 558

Text #19

Max Range: 2.0368. Min Range: -2.0368

Max Act: 1.7140. Min Act: -0.0002

Data Index: 111863 (C4 (Web Text))

Max Activating Token Index: 461