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

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

Neuron 2217 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0633. Min Act: -0.0001

Data Index: 138811 (C4 (Web Text))

Max Activating Token Index: 235

Text #1

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0525. Min Act: -0.0001

Data Index: 871655 (C4 (Web Text))

Max Activating Token Index: 284

Text #2

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0477. Min Act: -0.0001

Data Index: 129086 (C4 (Web Text))

Max Activating Token Index: 753

Text #3

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0391. Min Act: -0.0001

Data Index: 11730 (C4 (Web Text))

Max Activating Token Index: 680

Text #4

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0397. Min Act: -0.0001

Data Index: 634453 (C4 (Web Text))

Max Activating Token Index: 148

Text #5

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0358. Min Act: -0.0001

Data Index: 3540 (C4 (Web Text))

Max Activating Token Index: 238

Text #6

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0396. Min Act: -0.0001

Data Index: 661736 (C4 (Web Text))

Max Activating Token Index: 574

Text #7

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0384. Min Act: -0.0001

Data Index: 780231 (C4 (Web Text))

Max Activating Token Index: 146

Text #8

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0398. Min Act: -0.0002

Data Index: 1016218 (C4 (Web Text))

Max Activating Token Index: 921

Text #9

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0406. Min Act: -0.0001

Data Index: 14241 (C4 (Web Text))

Max Activating Token Index: 380

Text #10

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0386. Min Act: -0.0001

Data Index: 1219237 (C4 (Web Text))

Max Activating Token Index: 540

Text #11

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0387. Min Act: -0.0001

Data Index: 264441 (C4 (Web Text))

Max Activating Token Index: 690

Text #12

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0379. Min Act: -0.0001

Data Index: 803774 (C4 (Web Text))

Max Activating Token Index: 543

Text #13

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0374. Min Act: -0.0001

Data Index: 896576 (C4 (Web Text))

Max Activating Token Index: 245

Text #14

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0389. Min Act: -0.0001

Data Index: 707068 (C4 (Web Text))

Max Activating Token Index: 425

Text #15

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0353. Min Act: -0.0001

Data Index: 1155438 (C4 (Web Text))

Max Activating Token Index: 692

Text #16

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0386. Min Act: -0.0001

Data Index: 191859 (C4 (Web Text))

Max Activating Token Index: 160

Text #17

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0345. Min Act: -0.0001

Data Index: 856658 (C4 (Web Text))

Max Activating Token Index: 759

Text #18

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0378. Min Act: -0.0001

Data Index: 27916 (C4 (Web Text))

Max Activating Token Index: 489

Text #19

Max Range: 0.0633. Min Range: -0.0633

Max Act: 0.0354. Min Act: -0.0001

Data Index: 1200109 (C4 (Web Text))

Max Activating Token Index: 990