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

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

Neuron 1621 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: 1.2689. Min Range: -1.2689

Max Act: 1.2689. Min Act: -0.0002

Data Index: 126168 (C4 (Web Text))

Max Activating Token Index: 661

Text #1

Max Range: 1.2689. Min Range: -1.2689

Max Act: 1.1330. Min Act: -0.0002

Data Index: 310016 (C4 (Web Text))

Max Activating Token Index: 221

Text #2

Max Range: 1.2689. Min Range: -1.2689

Max Act: 1.0640. Min Act: -0.0002

Data Index: 221275 (C4 (Web Text))

Max Activating Token Index: 51

Text #3

Max Range: 1.2689. Min Range: -1.2689

Max Act: 1.0828. Min Act: -0.0002

Data Index: 5111 (C4 (Web Text))

Max Activating Token Index: 280

Text #4

Max Range: 1.2689. Min Range: -1.2689

Max Act: 1.0477. Min Act: -0.0002

Data Index: 695045 (C4 (Web Text))

Max Activating Token Index: 359

Text #5

Max Range: 1.2689. Min Range: -1.2689

Max Act: 1.0372. Min Act: -0.0002

Data Index: 970981 (C4 (Web Text))

Max Activating Token Index: 314

Text #6

Max Range: 1.2689. Min Range: -1.2689

Max Act: 1.0093. Min Act: -0.0002

Data Index: 137232 (C4 (Web Text))

Max Activating Token Index: 907

Text #7

Max Range: 1.2689. Min Range: -1.2689

Max Act: 1.0131. Min Act: -0.0002

Data Index: 1127560 (C4 (Web Text))

Max Activating Token Index: 259

Text #8

Max Range: 1.2689. Min Range: -1.2689

Max Act: 1.0219. Min Act: -0.0002

Data Index: 776098 (C4 (Web Text))

Max Activating Token Index: 793

Text #9

Max Range: 1.2689. Min Range: -1.2689

Max Act: 1.0047. Min Act: -0.0002

Data Index: 278488 (C4 (Web Text))

Max Activating Token Index: 559

Text #10

Max Range: 1.2689. Min Range: -1.2689

Max Act: 1.0084. Min Act: -0.0002

Data Index: 644696 (C4 (Web Text))

Max Activating Token Index: 367

Text #11

Max Range: 1.2689. Min Range: -1.2689

Max Act: 0.9821. Min Act: -0.0002

Data Index: 672324 (C4 (Web Text))

Max Activating Token Index: 178

Text #12

Max Range: 1.2689. Min Range: -1.2689

Max Act: 1.0092. Min Act: -0.0002

Data Index: 488846 (C4 (Web Text))

Max Activating Token Index: 919

Text #13

Max Range: 1.2689. Min Range: -1.2689

Max Act: 0.9833. Min Act: -0.0002

Data Index: 1218711 (C4 (Web Text))

Max Activating Token Index: 782

Text #14

Max Range: 1.2689. Min Range: -1.2689

Max Act: 0.9845. Min Act: -0.0003

Data Index: 910436 (C4 (Web Text))

Max Activating Token Index: 980

Text #15

Max Range: 1.2689. Min Range: -1.2689

Max Act: 0.9734. Min Act: -0.0002

Data Index: 454767 (C4 (Web Text))

Max Activating Token Index: 636

Text #16

Max Range: 1.2689. Min Range: -1.2689

Max Act: 0.9851. Min Act: -0.0002

Data Index: 838637 (C4 (Web Text))

Max Activating Token Index: 294

Text #17

Max Range: 1.2689. Min Range: -1.2689

Max Act: 0.9613. Min Act: -0.0002

Data Index: 912422 (C4 (Web Text))

Max Activating Token Index: 836

Text #18

Max Range: 1.2689. Min Range: -1.2689

Max Act: 0.9724. Min Act: -0.0002

Data Index: 1119816 (C4 (Web Text))

Max Activating Token Index: 132

Text #19

Max Range: 1.2689. Min Range: -1.2689

Max Act: 0.9647. Min Act: -0.0002

Data Index: 787700 (C4 (Web Text))

Max Activating Token Index: 170