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

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

Neuron 5163 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: 0.0575. Min Range: -0.0575

Max Act: 0.0566. Min Act: -0.0001

Data Index: 612860 (C4 (Web Text))

Max Activating Token Index: 55

Text #1

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0575. Min Act: -0.0001

Data Index: 1242496 (C4 (Web Text))

Max Activating Token Index: 280

Text #2

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0490. Min Act: -0.0001

Data Index: 1539795 (Python Code)

Max Activating Token Index: 382

Text #3

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0464. Min Act: -0.0001

Data Index: 1264067 (C4 (Web Text))

Max Activating Token Index: 172

Text #4

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0455. Min Act: -0.0001

Data Index: 730957 (C4 (Web Text))

Max Activating Token Index: 362

Text #5

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0480. Min Act: -0.0001

Data Index: 1500656 (Python Code)

Max Activating Token Index: 370

Text #6

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0465. Min Act: -0.0001

Data Index: 949997 (C4 (Web Text))

Max Activating Token Index: 254

Text #7

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0478. Min Act: -0.0001

Data Index: 52698 (C4 (Web Text))

Max Activating Token Index: 190

Text #8

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0430. Min Act: -0.0001

Data Index: 1527860 (Python Code)

Max Activating Token Index: 739

Text #9

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0446. Min Act: -0.0001

Data Index: 871363 (C4 (Web Text))

Max Activating Token Index: 486

Text #10

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0404. Min Act: -0.0001

Data Index: 853121 (C4 (Web Text))

Max Activating Token Index: 59

Text #11

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0410. Min Act: -0.0001

Data Index: 621780 (C4 (Web Text))

Max Activating Token Index: 16

Text #12

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0390. Min Act: -0.0001

Data Index: 1459923 (Python Code)

Max Activating Token Index: 243

Text #13

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0465. Min Act: -0.0001

Data Index: 606246 (C4 (Web Text))

Max Activating Token Index: 655

Text #14

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0462. Min Act: -0.0001

Data Index: 573200 (C4 (Web Text))

Max Activating Token Index: 676

Text #15

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0447. Min Act: -0.0001

Data Index: 979087 (C4 (Web Text))

Max Activating Token Index: 51

Text #16

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0419. Min Act: -0.0001

Data Index: 1253612 (C4 (Web Text))

Max Activating Token Index: 403

Text #17

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0429. Min Act: -0.0001

Data Index: 923081 (C4 (Web Text))

Max Activating Token Index: 643

Text #18

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0330. Min Act: -0.0001

Data Index: 1602931 (Python Code)

Max Activating Token Index: 965

Text #19

Max Range: 0.0575. Min Range: -0.0575

Max Act: 0.0438. Min Act: -0.0001

Data Index: 826847 (C4 (Web Text))

Max Activating Token Index: 168