Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1501 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0482. Min Act: -0.0002

Data Index: 1411398 (Python Code)

Max Activating Token Index: 479

Text #1

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0457. Min Act: -0.0002

Data Index: 1390786 (Python Code)

Max Activating Token Index: 491

Text #2

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0437. Min Act: -0.0003

Data Index: 1536773 (Python Code)

Max Activating Token Index: 820

Text #3

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0403. Min Act: -0.0002

Data Index: 1310018 (C4 (Web Text))

Max Activating Token Index: 934

Text #4

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0392. Min Act: -0.0002

Data Index: 624923 (C4 (Web Text))

Max Activating Token Index: 827

Text #5

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0390. Min Act: -0.0002

Data Index: 1632782 (Python Code)

Max Activating Token Index: 514

Text #6

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0374. Min Act: -0.0002

Data Index: 271604 (C4 (Web Text))

Max Activating Token Index: 440

Text #7

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0365. Min Act: -0.0002

Data Index: 650500 (C4 (Web Text))

Max Activating Token Index: 785

Text #8

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0372. Min Act: -0.0002

Data Index: 47497 (C4 (Web Text))

Max Activating Token Index: 939

Text #9

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0369. Min Act: -0.0002

Data Index: 1620218 (Python Code)

Max Activating Token Index: 862

Text #10

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0349. Min Act: -0.0003

Data Index: 1511319 (Python Code)

Max Activating Token Index: 641

Text #11

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0353. Min Act: -0.0002

Data Index: 1523658 (Python Code)

Max Activating Token Index: 863

Text #12

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0350. Min Act: -0.0002

Data Index: 1581464 (Python Code)

Max Activating Token Index: 312

Text #13

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0341. Min Act: -0.0002

Data Index: 1559157 (Python Code)

Max Activating Token Index: 636

Text #14

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0341. Min Act: -0.0002

Data Index: 1493173 (Python Code)

Max Activating Token Index: 648

Text #15

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0385. Min Act: -0.0003

Data Index: 6981 (C4 (Web Text))

Max Activating Token Index: 697

Text #16

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0350. Min Act: -0.0002

Data Index: 1509031 (Python Code)

Max Activating Token Index: 180

Text #17

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0346. Min Act: -0.0002

Data Index: 1436977 (Python Code)

Max Activating Token Index: 920

Text #18

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0346. Min Act: -0.0003

Data Index: 1368633 (Python Code)

Max Activating Token Index: 695

Text #19

Max Range: 0.0482. Min Range: -0.0482

Max Act: 0.0333. Min Act: -0.0002

Data Index: 1534411 (Python Code)

Max Activating Token Index: 632