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

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

Neuron 1544 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1791. Min Act: -0.0002

Data Index: 164934 (C4 (Web Text))

Max Activating Token Index: 984

Text #1

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1572. Min Act: -0.0002

Data Index: 789419 (C4 (Web Text))

Max Activating Token Index: 203

Text #2

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1590. Min Act: -0.0002

Data Index: 475632 (C4 (Web Text))

Max Activating Token Index: 927

Text #3

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1575. Min Act: -0.0002

Data Index: 462852 (C4 (Web Text))

Max Activating Token Index: 150

Text #4

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1535. Min Act: -0.0002

Data Index: 493874 (C4 (Web Text))

Max Activating Token Index: 908

Text #5

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1484. Min Act: -0.0002

Data Index: 962934 (C4 (Web Text))

Max Activating Token Index: 71

Text #6

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1448. Min Act: -0.0002

Data Index: 281120 (C4 (Web Text))

Max Activating Token Index: 310

Text #7

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1514. Min Act: -0.0002

Data Index: 505441 (C4 (Web Text))

Max Activating Token Index: 676

Text #8

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1415. Min Act: -0.0002

Data Index: 257798 (C4 (Web Text))

Max Activating Token Index: 53

Text #9

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1428. Min Act: -0.0002

Data Index: 376308 (C4 (Web Text))

Max Activating Token Index: 847

Text #10

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1412. Min Act: -0.0002

Data Index: 869114 (C4 (Web Text))

Max Activating Token Index: 887

Text #11

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1422. Min Act: -0.0002

Data Index: 1093906 (C4 (Web Text))

Max Activating Token Index: 211

Text #12

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1388. Min Act: -0.0003

Data Index: 268843 (C4 (Web Text))

Max Activating Token Index: 971

Text #13

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1393. Min Act: -0.0002

Data Index: 599929 (C4 (Web Text))

Max Activating Token Index: 774

Text #14

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1374. Min Act: -0.0002

Data Index: 78918 (C4 (Web Text))

Max Activating Token Index: 415

Text #15

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1374. Min Act: -0.0002

Data Index: 714108 (C4 (Web Text))

Max Activating Token Index: 71

Text #16

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1396. Min Act: -0.0002

Data Index: 1093819 (C4 (Web Text))

Max Activating Token Index: 527

Text #17

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1346. Min Act: -0.0002

Data Index: 1057132 (C4 (Web Text))

Max Activating Token Index: 22

Text #18

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1339. Min Act: -0.0002

Data Index: 396647 (C4 (Web Text))

Max Activating Token Index: 49

Text #19

Max Range: 0.1791. Min Range: -0.1791

Max Act: 0.1333. Min Act: -0.0003

Data Index: 581810 (C4 (Web Text))

Max Activating Token Index: 531