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

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

Neuron 2452 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0473. Min Act: -0.0002

Data Index: 1454237 (Python Code)

Max Activating Token Index: 524

Text #1

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0482. Min Act: -0.0002

Data Index: 1541093 (Python Code)

Max Activating Token Index: 683

Text #2

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0490. Min Act: -0.0002

Data Index: 1493862 (Python Code)

Max Activating Token Index: 714

Text #3

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0455. Min Act: -0.0002

Data Index: 132287 (C4 (Web Text))

Max Activating Token Index: 468

Text #4

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0455. Min Act: -0.0002

Data Index: 1384216 (Python Code)

Max Activating Token Index: 352

Text #5

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0425. Min Act: -0.0002

Data Index: 1604503 (Python Code)

Max Activating Token Index: 305

Text #6

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0425. Min Act: -0.0002

Data Index: 1423444 (Python Code)

Max Activating Token Index: 218

Text #7

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0404. Min Act: -0.0002

Data Index: 1593919 (Python Code)

Max Activating Token Index: 461

Text #8

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0418. Min Act: -0.0002

Data Index: 2620 (C4 (Web Text))

Max Activating Token Index: 494

Text #9

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0415. Min Act: -0.0002

Data Index: 1384229 (Python Code)

Max Activating Token Index: 55

Text #10

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0413. Min Act: -0.0002

Data Index: 1302204 (C4 (Web Text))

Max Activating Token Index: 650

Text #11

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0399. Min Act: -0.0002

Data Index: 1595187 (Python Code)

Max Activating Token Index: 223

Text #12

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0405. Min Act: -0.0002

Data Index: 922960 (C4 (Web Text))

Max Activating Token Index: 834

Text #13

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0393. Min Act: -0.0002

Data Index: 395534 (C4 (Web Text))

Max Activating Token Index: 670

Text #14

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0393. Min Act: -0.0002

Data Index: 667917 (C4 (Web Text))

Max Activating Token Index: 661

Text #15

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0384. Min Act: -0.0002

Data Index: 1651696 (Python Code)

Max Activating Token Index: 610

Text #16

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0388. Min Act: -0.0002

Data Index: 1506193 (Python Code)

Max Activating Token Index: 919

Text #17

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0383. Min Act: -0.0002

Data Index: 1411255 (Python Code)

Max Activating Token Index: 130

Text #18

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0381. Min Act: -0.0002

Data Index: 573636 (C4 (Web Text))

Max Activating Token Index: 142

Text #19

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0394. Min Act: -0.0002

Data Index: 1284051 (C4 (Web Text))

Max Activating Token Index: 836