Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2168 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1376. Min Act: -0.0000

Data Index: 127870 (C4 (Web Text))

Max Activating Token Index: 505

Text #1

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1274. Min Act: -0.0000

Data Index: 1269890 (C4 (Web Text))

Max Activating Token Index: 538

Text #2

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1056. Min Act: -0.0000

Data Index: 1356370 (C4 (Web Text))

Max Activating Token Index: 808

Text #3

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1058. Min Act: -0.0000

Data Index: 1207700 (C4 (Web Text))

Max Activating Token Index: 222

Text #4

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.0988. Min Act: -0.0000

Data Index: 735569 (C4 (Web Text))

Max Activating Token Index: 437

Text #5

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.0948. Min Act: -0.0000

Data Index: 410895 (C4 (Web Text))

Max Activating Token Index: 861

Text #6

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.0974. Min Act: -0.0000

Data Index: 1232596 (C4 (Web Text))

Max Activating Token Index: 642

Text #7

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.0972. Min Act: -0.0000

Data Index: 1250036 (C4 (Web Text))

Max Activating Token Index: 222

Text #8

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.0917. Min Act: -0.0000

Data Index: 1077341 (C4 (Web Text))

Max Activating Token Index: 638

Text #9

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.0948. Min Act: -0.0000

Data Index: 451736 (C4 (Web Text))

Max Activating Token Index: 388

Text #10

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.0845. Min Act: -0.0000

Data Index: 134350 (C4 (Web Text))

Max Activating Token Index: 901

Text #11

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.0864. Min Act: -0.0000

Data Index: 476223 (C4 (Web Text))

Max Activating Token Index: 851

Text #12

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.0760. Min Act: -0.0000

Data Index: 1228862 (C4 (Web Text))

Max Activating Token Index: 197

Text #13

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.0909. Min Act: -0.0000

Data Index: 482865 (C4 (Web Text))

Max Activating Token Index: 399

Text #14

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.0839. Min Act: -0.0000

Data Index: 494834 (C4 (Web Text))

Max Activating Token Index: 368

Text #15

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.0855. Min Act: -0.0000

Data Index: 1346712 (C4 (Web Text))

Max Activating Token Index: 178

Text #16

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.0820. Min Act: -0.0001

Data Index: 711850 (C4 (Web Text))

Max Activating Token Index: 658

Text #17

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.0810. Min Act: -0.0000

Data Index: 461559 (C4 (Web Text))

Max Activating Token Index: 694

Text #18

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.0818. Min Act: -0.0000

Data Index: 1151071 (C4 (Web Text))

Max Activating Token Index: 23

Text #19

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.0779. Min Act: -0.0000

Data Index: 1343296 (C4 (Web Text))

Max Activating Token Index: 220