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

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

Neuron 1819 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8356. Min Range: -0.8356

Max Act: 0.8356. Min Act: -0.0000

Data Index: 1145243 (C4 (Web Text))

Max Activating Token Index: 866

Text #1

Max Range: 0.8356. Min Range: -0.8356

Max Act: 0.7797. Min Act: -0.0000

Data Index: 938944 (C4 (Web Text))

Max Activating Token Index: 362

Text #2

Max Range: 0.8356. Min Range: -0.8356

Max Act: 0.7014. Min Act: -0.0000

Data Index: 935888 (C4 (Web Text))

Max Activating Token Index: 416

Text #3

Max Range: 0.8356. Min Range: -0.8356

Max Act: 0.7081. Min Act: -0.0000

Data Index: 467601 (C4 (Web Text))

Max Activating Token Index: 39

Text #4

Max Range: 0.8356. Min Range: -0.8356

Max Act: 0.6939. Min Act: -0.0000

Data Index: 1177578 (C4 (Web Text))

Max Activating Token Index: 474

Text #5

Max Range: 0.8356. Min Range: -0.8356

Max Act: 0.6484. Min Act: -0.0000

Data Index: 6718 (C4 (Web Text))

Max Activating Token Index: 309

Text #6

Max Range: 0.8356. Min Range: -0.8356

Max Act: 0.6814. Min Act: -0.0000

Data Index: 702314 (C4 (Web Text))

Max Activating Token Index: 530

Text #7

Max Range: 0.8356. Min Range: -0.8356

Max Act: 0.6715. Min Act: -0.0000

Data Index: 454344 (C4 (Web Text))

Max Activating Token Index: 624

Text #8

Max Range: 0.8356. Min Range: -0.8356

Max Act: 0.7231. Min Act: -0.0000

Data Index: 467783 (C4 (Web Text))

Max Activating Token Index: 715

Text #9

Max Range: 0.8356. Min Range: -0.8356

Max Act: 0.6562. Min Act: -0.0000

Data Index: 1178799 (C4 (Web Text))

Max Activating Token Index: 510

Text #10

Max Range: 0.8356. Min Range: -0.8356

Max Act: 0.6770. Min Act: -0.0000

Data Index: 408545 (C4 (Web Text))

Max Activating Token Index: 20

Text #11

Max Range: 0.8356. Min Range: -0.8356

Max Act: 0.6510. Min Act: -0.0000

Data Index: 193497 (C4 (Web Text))

Max Activating Token Index: 651

Text #12

Max Range: 0.8356. Min Range: -0.8356

Max Act: 0.6706. Min Act: -0.0000

Data Index: 1133503 (C4 (Web Text))

Max Activating Token Index: 187

Text #13

Max Range: 0.8356. Min Range: -0.8356

Max Act: 0.6646. Min Act: -0.0000

Data Index: 1207625 (C4 (Web Text))

Max Activating Token Index: 212

Text #14

Max Range: 0.8356. Min Range: -0.8356

Max Act: 0.6389. Min Act: -0.0000

Data Index: 663273 (C4 (Web Text))

Max Activating Token Index: 7

Text #15

Max Range: 0.8356. Min Range: -0.8356

Max Act: 0.6983. Min Act: -0.0000

Data Index: 578608 (C4 (Web Text))

Max Activating Token Index: 19

Text #16

Max Range: 0.8356. Min Range: -0.8356

Max Act: 0.6279. Min Act: -0.0000

Data Index: 1141704 (C4 (Web Text))

Max Activating Token Index: 526

Text #17

Max Range: 0.8356. Min Range: -0.8356

Max Act: 0.6420. Min Act: -0.0000

Data Index: 1169444 (C4 (Web Text))

Max Activating Token Index: 418

Text #18

Max Range: 0.8356. Min Range: -0.8356

Max Act: 0.6188. Min Act: -0.0000

Data Index: 296096 (C4 (Web Text))

Max Activating Token Index: 293

Text #19

Max Range: 0.8356. Min Range: -0.8356

Max Act: 0.6558. Min Act: -0.0000

Data Index: 1120382 (C4 (Web Text))

Max Activating Token Index: 416