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

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

Neuron 2783 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: 0.0619. Min Range: -0.0619

Max Act: 0.0619. Min Act: -0.0002

Data Index: 1591493 (Python Code)

Max Activating Token Index: 1006

Text #1

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0543. Min Act: -0.0002

Data Index: 1564627 (Python Code)

Max Activating Token Index: 7

Text #2

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0511. Min Act: -0.0002

Data Index: 1097033 (C4 (Web Text))

Max Activating Token Index: 13

Text #3

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0470. Min Act: -0.0002

Data Index: 1066925 (C4 (Web Text))

Max Activating Token Index: 554

Text #4

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0452. Min Act: -0.0002

Data Index: 434698 (C4 (Web Text))

Max Activating Token Index: 229

Text #5

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0448. Min Act: -0.0002

Data Index: 1356459 (C4 (Web Text))

Max Activating Token Index: 275

Text #6

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0433. Min Act: -0.0002

Data Index: 1369284 (Python Code)

Max Activating Token Index: 319

Text #7

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0427. Min Act: -0.0002

Data Index: 262723 (C4 (Web Text))

Max Activating Token Index: 307

Text #8

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0435. Min Act: -0.0002

Data Index: 1278295 (C4 (Web Text))

Max Activating Token Index: 66

Text #9

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0425. Min Act: -0.0002

Data Index: 1465857 (Python Code)

Max Activating Token Index: 216

Text #10

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0413. Min Act: -0.0002

Data Index: 205400 (C4 (Web Text))

Max Activating Token Index: 72

Text #11

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0413. Min Act: -0.0002

Data Index: 1269829 (C4 (Web Text))

Max Activating Token Index: 243

Text #12

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0412. Min Act: -0.0002

Data Index: 1474426 (Python Code)

Max Activating Token Index: 104

Text #13

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0404. Min Act: -0.0002

Data Index: 1218204 (C4 (Web Text))

Max Activating Token Index: 991

Text #14

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0407. Min Act: -0.0002

Data Index: 1486830 (Python Code)

Max Activating Token Index: 970

Text #15

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0403. Min Act: -0.0003

Data Index: 505906 (C4 (Web Text))

Max Activating Token Index: 349

Text #16

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0394. Min Act: -0.0002

Data Index: 113541 (C4 (Web Text))

Max Activating Token Index: 510

Text #17

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0398. Min Act: -0.0002

Data Index: 804638 (C4 (Web Text))

Max Activating Token Index: 468

Text #18

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0387. Min Act: -0.0002

Data Index: 462261 (C4 (Web Text))

Max Activating Token Index: 667

Text #19

Max Range: 0.0619. Min Range: -0.0619

Max Act: 0.0396. Min Act: -0.0002

Data Index: 118010 (C4 (Web Text))

Max Activating Token Index: 488