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

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

Neuron 1282 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9361. Min Range: -0.9361

Max Act: 0.9361. Min Act: -0.0000

Data Index: 796665 (C4 (Web Text))

Max Activating Token Index: 268

Text #1

Max Range: 0.9361. Min Range: -0.9361

Max Act: 0.8009. Min Act: -0.0000

Data Index: 1302591 (C4 (Web Text))

Max Activating Token Index: 9

Text #2

Max Range: 0.9361. Min Range: -0.9361

Max Act: 0.6264. Min Act: -0.0000

Data Index: 76555 (C4 (Web Text))

Max Activating Token Index: 323

Text #3

Max Range: 0.9361. Min Range: -0.9361

Max Act: 0.6369. Min Act: -0.0000

Data Index: 93206 (C4 (Web Text))

Max Activating Token Index: 725

Text #4

Max Range: 0.9361. Min Range: -0.9361

Max Act: 0.5638. Min Act: -0.0000

Data Index: 1038864 (C4 (Web Text))

Max Activating Token Index: 20

Text #5

Max Range: 0.9361. Min Range: -0.9361

Max Act: 0.5466. Min Act: -0.0000

Data Index: 1240845 (C4 (Web Text))

Max Activating Token Index: 601

Text #6

Max Range: 0.9361. Min Range: -0.9361

Max Act: 0.4916. Min Act: -0.0000

Data Index: 1205860 (C4 (Web Text))

Max Activating Token Index: 861

Text #7

Max Range: 0.9361. Min Range: -0.9361

Max Act: 0.4810. Min Act: -0.0000

Data Index: 1289609 (C4 (Web Text))

Max Activating Token Index: 912

Text #8

Max Range: 0.9361. Min Range: -0.9361

Max Act: 0.4955. Min Act: -0.0000

Data Index: 552817 (C4 (Web Text))

Max Activating Token Index: 950

Text #9

Max Range: 0.9361. Min Range: -0.9361

Max Act: 0.4736. Min Act: -0.0000

Data Index: 379100 (C4 (Web Text))

Max Activating Token Index: 289

Text #10

Max Range: 0.9361. Min Range: -0.9361

Max Act: 0.4670. Min Act: -0.0000

Data Index: 429079 (C4 (Web Text))

Max Activating Token Index: 676

Text #11

Max Range: 0.9361. Min Range: -0.9361

Max Act: 0.4528. Min Act: -0.0000

Data Index: 827193 (C4 (Web Text))

Max Activating Token Index: 1012

Text #12

Max Range: 0.9361. Min Range: -0.9361

Max Act: 0.4506. Min Act: -0.0000

Data Index: 1149710 (C4 (Web Text))

Max Activating Token Index: 285

Text #13

Max Range: 0.9361. Min Range: -0.9361

Max Act: 0.4375. Min Act: -0.0000

Data Index: 887791 (C4 (Web Text))

Max Activating Token Index: 860

Text #14

Max Range: 0.9361. Min Range: -0.9361

Max Act: 0.4679. Min Act: -0.0000

Data Index: 1073585 (C4 (Web Text))

Max Activating Token Index: 246

Text #15

Max Range: 0.9361. Min Range: -0.9361

Max Act: 0.4176. Min Act: -0.0000

Data Index: 494155 (C4 (Web Text))

Max Activating Token Index: 232

Text #16

Max Range: 0.9361. Min Range: -0.9361

Max Act: 0.4443. Min Act: -0.0000

Data Index: 776935 (C4 (Web Text))

Max Activating Token Index: 991

Text #17

Max Range: 0.9361. Min Range: -0.9361

Max Act: 0.4222. Min Act: -0.0000

Data Index: 1087348 (C4 (Web Text))

Max Activating Token Index: 539

Text #18

Max Range: 0.9361. Min Range: -0.9361

Max Act: 0.4037. Min Act: -0.0000

Data Index: 476005 (C4 (Web Text))

Max Activating Token Index: 332

Text #19

Max Range: 0.9361. Min Range: -0.9361

Max Act: 0.4278. Min Act: -0.0000

Data Index: 701857 (C4 (Web Text))

Max Activating Token Index: 365