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

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

Neuron 1725 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: 0.2351. Min Range: -0.2351

Max Act: 0.2351. Min Act: -0.0003

Data Index: 808749 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.2351. Min Range: -0.2351

Max Act: 0.2046. Min Act: -0.0003

Data Index: 654305 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.2351. Min Range: -0.2351

Max Act: 0.1730. Min Act: -0.0003

Data Index: 1012068 (C4 (Web Text))

Max Activating Token Index: 603

Text #3

Max Range: 0.2351. Min Range: -0.2351

Max Act: 0.1608. Min Act: -0.0003

Data Index: 742018 (C4 (Web Text))

Max Activating Token Index: 845

Text #4

Max Range: 0.2351. Min Range: -0.2351

Max Act: 0.1664. Min Act: -0.0003

Data Index: 916909 (C4 (Web Text))

Max Activating Token Index: 861

Text #5

Max Range: 0.2351. Min Range: -0.2351

Max Act: 0.1697. Min Act: -0.0003

Data Index: 492482 (C4 (Web Text))

Max Activating Token Index: 240

Text #6

Max Range: 0.2351. Min Range: -0.2351

Max Act: 0.1520. Min Act: -0.0003

Data Index: 617088 (C4 (Web Text))

Max Activating Token Index: 388

Text #7

Max Range: 0.2351. Min Range: -0.2351

Max Act: 0.1568. Min Act: -0.0003

Data Index: 71541 (C4 (Web Text))

Max Activating Token Index: 921

Text #8

Max Range: 0.2351. Min Range: -0.2351

Max Act: 0.1504. Min Act: -0.0003

Data Index: 756668 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.2351. Min Range: -0.2351

Max Act: 0.1437. Min Act: -0.0003

Data Index: 18436 (C4 (Web Text))

Max Activating Token Index: 939

Text #10

Max Range: 0.2351. Min Range: -0.2351

Max Act: 0.1329. Min Act: -0.0003

Data Index: 1328067 (C4 (Web Text))

Max Activating Token Index: 627

Text #11

Max Range: 0.2351. Min Range: -0.2351

Max Act: 0.1366. Min Act: -0.0003

Data Index: 867050 (C4 (Web Text))

Max Activating Token Index: 475

Text #12

Max Range: 0.2351. Min Range: -0.2351

Max Act: 0.1429. Min Act: -0.0003

Data Index: 128728 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.2351. Min Range: -0.2351

Max Act: 0.1263. Min Act: -0.0003

Data Index: 963036 (C4 (Web Text))

Max Activating Token Index: 514

Text #14

Max Range: 0.2351. Min Range: -0.2351

Max Act: 0.1400. Min Act: -0.0003

Data Index: 143292 (C4 (Web Text))

Max Activating Token Index: 443

Text #15

Max Range: 0.2351. Min Range: -0.2351

Max Act: 0.1516. Min Act: -0.0003

Data Index: 49735 (C4 (Web Text))

Max Activating Token Index: 318

Text #16

Max Range: 0.2351. Min Range: -0.2351

Max Act: 0.1363. Min Act: -0.0003

Data Index: 150344 (C4 (Web Text))

Max Activating Token Index: 587

Text #17

Max Range: 0.2351. Min Range: -0.2351

Max Act: 0.1362. Min Act: -0.0003

Data Index: 740050 (C4 (Web Text))

Max Activating Token Index: 540

Text #18

Max Range: 0.2351. Min Range: -0.2351

Max Act: 0.1351. Min Act: -0.0003

Data Index: 630559 (C4 (Web Text))

Max Activating Token Index: 167

Text #19

Max Range: 0.2351. Min Range: -0.2351

Max Act: 0.1297. Min Act: -0.0003

Data Index: 192248 (C4 (Web Text))

Max Activating Token Index: 30