Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1271 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.9357. Min Range: -0.9357

Max Act: 0.9357. Min Act: -0.0003

Data Index: 624494 (C4 (Web Text))

Max Activating Token Index: 300

Text #1

Max Range: 0.9357. Min Range: -0.9357

Max Act: 0.8547. Min Act: -0.0003

Data Index: 926736 (C4 (Web Text))

Max Activating Token Index: 614

Text #2

Max Range: 0.9357. Min Range: -0.9357

Max Act: 0.8640. Min Act: -0.0003

Data Index: 170260 (C4 (Web Text))

Max Activating Token Index: 692

Text #3

Max Range: 0.9357. Min Range: -0.9357

Max Act: 0.7419. Min Act: -0.0003

Data Index: 1317937 (C4 (Web Text))

Max Activating Token Index: 187

Text #4

Max Range: 0.9357. Min Range: -0.9357

Max Act: 0.7600. Min Act: -0.0003

Data Index: 956816 (C4 (Web Text))

Max Activating Token Index: 737

Text #5

Max Range: 0.9357. Min Range: -0.9357

Max Act: 0.7804. Min Act: -0.0003

Data Index: 333135 (C4 (Web Text))

Max Activating Token Index: 555

Text #6

Max Range: 0.9357. Min Range: -0.9357

Max Act: 0.7268. Min Act: -0.0003

Data Index: 709558 (C4 (Web Text))

Max Activating Token Index: 154

Text #7

Max Range: 0.9357. Min Range: -0.9357

Max Act: 0.6812. Min Act: -0.0003

Data Index: 908355 (C4 (Web Text))

Max Activating Token Index: 928

Text #8

Max Range: 0.9357. Min Range: -0.9357

Max Act: 0.6962. Min Act: -0.0003

Data Index: 341488 (C4 (Web Text))

Max Activating Token Index: 63

Text #9

Max Range: 0.9357. Min Range: -0.9357

Max Act: 0.6373. Min Act: -0.0003

Data Index: 200459 (C4 (Web Text))

Max Activating Token Index: 690

Text #10

Max Range: 0.9357. Min Range: -0.9357

Max Act: 0.6547. Min Act: -0.0003

Data Index: 472840 (C4 (Web Text))

Max Activating Token Index: 634

Text #11

Max Range: 0.9357. Min Range: -0.9357

Max Act: 0.6766. Min Act: -0.0003

Data Index: 601198 (C4 (Web Text))

Max Activating Token Index: 602

Text #12

Max Range: 0.9357. Min Range: -0.9357

Max Act: 0.6539. Min Act: -0.0003

Data Index: 630690 (C4 (Web Text))

Max Activating Token Index: 636

Text #13

Max Range: 0.9357. Min Range: -0.9357

Max Act: 0.6567. Min Act: -0.0003

Data Index: 63339 (C4 (Web Text))

Max Activating Token Index: 958

Text #14

Max Range: 0.9357. Min Range: -0.9357

Max Act: 0.6449. Min Act: -0.0003

Data Index: 926066 (C4 (Web Text))

Max Activating Token Index: 512

Text #15

Max Range: 0.9357. Min Range: -0.9357

Max Act: 0.6412. Min Act: -0.0003

Data Index: 914935 (C4 (Web Text))

Max Activating Token Index: 261

Text #16

Max Range: 0.9357. Min Range: -0.9357

Max Act: 0.6435. Min Act: -0.0003

Data Index: 330057 (C4 (Web Text))

Max Activating Token Index: 477

Text #17

Max Range: 0.9357. Min Range: -0.9357

Max Act: 0.6745. Min Act: -0.0003

Data Index: 81942 (C4 (Web Text))

Max Activating Token Index: 361

Text #18

Max Range: 0.9357. Min Range: -0.9357

Max Act: 0.6662. Min Act: -0.0003

Data Index: 591126 (C4 (Web Text))

Max Activating Token Index: 306

Text #19

Max Range: 0.9357. Min Range: -0.9357

Max Act: 0.6213. Min Act: -0.0003

Data Index: 444025 (C4 (Web Text))

Max Activating Token Index: 869