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

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

Neuron 979 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4542. Min Range: -1.4542

Max Act: 1.4542. Min Act: -0.0000

Data Index: 1396600 (Python Code)

Max Activating Token Index: 610

Text #1

Max Range: 1.4542. Min Range: -1.4542

Max Act: 1.3895. Min Act: -0.0000

Data Index: 1584760 (Python Code)

Max Activating Token Index: 57

Text #2

Max Range: 1.4542. Min Range: -1.4542

Max Act: 1.2723. Min Act: -0.0000

Data Index: 331872 (C4 (Web Text))

Max Activating Token Index: 139

Text #3

Max Range: 1.4542. Min Range: -1.4542

Max Act: 1.2455. Min Act: -0.0000

Data Index: 1491360 (Python Code)

Max Activating Token Index: 232

Text #4

Max Range: 1.4542. Min Range: -1.4542

Max Act: 1.2041. Min Act: -0.0000

Data Index: 272041 (C4 (Web Text))

Max Activating Token Index: 76

Text #5

Max Range: 1.4542. Min Range: -1.4542

Max Act: 1.2375. Min Act: -0.0000

Data Index: 959779 (C4 (Web Text))

Max Activating Token Index: 402

Text #6

Max Range: 1.4542. Min Range: -1.4542

Max Act: 1.2349. Min Act: -0.0000

Data Index: 1038873 (C4 (Web Text))

Max Activating Token Index: 805

Text #7

Max Range: 1.4542. Min Range: -1.4542

Max Act: 1.2338. Min Act: -0.0000

Data Index: 1290495 (C4 (Web Text))

Max Activating Token Index: 849

Text #8

Max Range: 1.4542. Min Range: -1.4542

Max Act: 1.1319. Min Act: -0.0000

Data Index: 1076568 (C4 (Web Text))

Max Activating Token Index: 758

Text #9

Max Range: 1.4542. Min Range: -1.4542

Max Act: 1.1909. Min Act: -0.0000

Data Index: 562322 (C4 (Web Text))

Max Activating Token Index: 73

Text #10

Max Range: 1.4542. Min Range: -1.4542

Max Act: 1.1788. Min Act: -0.0000

Data Index: 1441737 (Python Code)

Max Activating Token Index: 23

Text #11

Max Range: 1.4542. Min Range: -1.4542

Max Act: 1.1546. Min Act: -0.0000

Data Index: 1553714 (Python Code)

Max Activating Token Index: 633

Text #12

Max Range: 1.4542. Min Range: -1.4542

Max Act: 1.1466. Min Act: -0.0000

Data Index: 1357165 (C4 (Web Text))

Max Activating Token Index: 45

Text #13

Max Range: 1.4542. Min Range: -1.4542

Max Act: 1.1088. Min Act: -0.0000

Data Index: 1515200 (Python Code)

Max Activating Token Index: 6

Text #14

Max Range: 1.4542. Min Range: -1.4542

Max Act: 1.1237. Min Act: -0.0000

Data Index: 1471246 (Python Code)

Max Activating Token Index: 1019

Text #15

Max Range: 1.4542. Min Range: -1.4542

Max Act: 1.1480. Min Act: -0.0000

Data Index: 1247878 (C4 (Web Text))

Max Activating Token Index: 43

Text #16

Max Range: 1.4542. Min Range: -1.4542

Max Act: 1.1537. Min Act: -0.0000

Data Index: 309476 (C4 (Web Text))

Max Activating Token Index: 26

Text #17

Max Range: 1.4542. Min Range: -1.4542

Max Act: 1.1150. Min Act: -0.0000

Data Index: 1591120 (Python Code)

Max Activating Token Index: 791

Text #18

Max Range: 1.4542. Min Range: -1.4542

Max Act: 1.1428. Min Act: -0.0000

Data Index: 1398060 (Python Code)

Max Activating Token Index: 8

Text #19

Max Range: 1.4542. Min Range: -1.4542

Max Act: 1.0767. Min Act: -0.0000

Data Index: 497789 (C4 (Web Text))

Max Activating Token Index: 7