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

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

Neuron 1762 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1643. Min Act: -0.0006

Data Index: 990130 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1504. Min Act: -0.0006

Data Index: 1231942 (C4 (Web Text))

Max Activating Token Index: 29

Text #2

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1556. Min Act: -0.0006

Data Index: 1011882 (C4 (Web Text))

Max Activating Token Index: 697

Text #3

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1456. Min Act: -0.0005

Data Index: 330056 (C4 (Web Text))

Max Activating Token Index: 336

Text #4

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1500. Min Act: -0.0005

Data Index: 467102 (C4 (Web Text))

Max Activating Token Index: 16

Text #5

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1429. Min Act: -0.0005

Data Index: 1090653 (C4 (Web Text))

Max Activating Token Index: 9

Text #6

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1475. Min Act: -0.0005

Data Index: 189394 (C4 (Web Text))

Max Activating Token Index: 17

Text #7

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1447. Min Act: -0.0006

Data Index: 692452 (C4 (Web Text))

Max Activating Token Index: 31

Text #8

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1457. Min Act: -0.0006

Data Index: 367824 (C4 (Web Text))

Max Activating Token Index: 388

Text #9

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1375. Min Act: -0.0006

Data Index: 991987 (C4 (Web Text))

Max Activating Token Index: 16

Text #10

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1425. Min Act: -0.0005

Data Index: 1019057 (C4 (Web Text))

Max Activating Token Index: 16

Text #11

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1422. Min Act: -0.0006

Data Index: 563814 (C4 (Web Text))

Max Activating Token Index: 12

Text #12

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1417. Min Act: -0.0005

Data Index: 176824 (C4 (Web Text))

Max Activating Token Index: 16

Text #13

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1429. Min Act: -0.0005

Data Index: 818015 (C4 (Web Text))

Max Activating Token Index: 14

Text #14

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1374. Min Act: -0.0005

Data Index: 1191325 (C4 (Web Text))

Max Activating Token Index: 754

Text #15

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1396. Min Act: -0.0005

Data Index: 395016 (C4 (Web Text))

Max Activating Token Index: 15

Text #16

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1397. Min Act: -0.0005

Data Index: 1092002 (C4 (Web Text))

Max Activating Token Index: 9

Text #17

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1394. Min Act: -0.0006

Data Index: 279957 (C4 (Web Text))

Max Activating Token Index: 126

Text #18

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1394. Min Act: -0.0005

Data Index: 1069973 (C4 (Web Text))

Max Activating Token Index: 13

Text #19

Max Range: 0.1643. Min Range: -0.1643

Max Act: 0.1391. Min Act: -0.0006

Data Index: 337681 (C4 (Web Text))

Max Activating Token Index: 971