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

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

Neuron 1732 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0532. Min Act: -0.0002

Data Index: 1170099 (C4 (Web Text))

Max Activating Token Index: 447

Text #1

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0486. Min Act: -0.0002

Data Index: 1209908 (C4 (Web Text))

Max Activating Token Index: 765

Text #2

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0432. Min Act: -0.0002

Data Index: 245721 (C4 (Web Text))

Max Activating Token Index: 368

Text #3

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0426. Min Act: -0.0002

Data Index: 372567 (C4 (Web Text))

Max Activating Token Index: 227

Text #4

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0434. Min Act: -0.0002

Data Index: 664105 (C4 (Web Text))

Max Activating Token Index: 235

Text #5

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0408. Min Act: -0.0002

Data Index: 407510 (C4 (Web Text))

Max Activating Token Index: 425

Text #6

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0424. Min Act: -0.0002

Data Index: 256869 (C4 (Web Text))

Max Activating Token Index: 613

Text #7

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0400. Min Act: -0.0002

Data Index: 1021042 (C4 (Web Text))

Max Activating Token Index: 535

Text #8

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0395. Min Act: -0.0002

Data Index: 133710 (C4 (Web Text))

Max Activating Token Index: 630

Text #9

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0394. Min Act: -0.0002

Data Index: 812206 (C4 (Web Text))

Max Activating Token Index: 448

Text #10

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0407. Min Act: -0.0002

Data Index: 248710 (C4 (Web Text))

Max Activating Token Index: 547

Text #11

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0393. Min Act: -0.0002

Data Index: 1330621 (C4 (Web Text))

Max Activating Token Index: 466

Text #12

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0383. Min Act: -0.0002

Data Index: 664771 (C4 (Web Text))

Max Activating Token Index: 393

Text #13

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0398. Min Act: -0.0002

Data Index: 417447 (C4 (Web Text))

Max Activating Token Index: 569

Text #14

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0385. Min Act: -0.0002

Data Index: 1341597 (C4 (Web Text))

Max Activating Token Index: 23

Text #15

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0382. Min Act: -0.0002

Data Index: 848408 (C4 (Web Text))

Max Activating Token Index: 120

Text #16

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0380. Min Act: -0.0002

Data Index: 1217069 (C4 (Web Text))

Max Activating Token Index: 34

Text #17

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0393. Min Act: -0.0002

Data Index: 109235 (C4 (Web Text))

Max Activating Token Index: 965

Text #18

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0394. Min Act: -0.0002

Data Index: 161835 (C4 (Web Text))

Max Activating Token Index: 602

Text #19

Max Range: 0.0532. Min Range: -0.0532

Max Act: 0.0377. Min Act: -0.0002

Data Index: 1155300 (C4 (Web Text))

Max Activating Token Index: 359