Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1453 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2123. Min Range: -0.2123

Max Act: 0.2123. Min Act: -0.0000

Data Index: 977467 (C4 (Web Text))

Max Activating Token Index: 187

Text #1

Max Range: 0.2123. Min Range: -0.2123

Max Act: 0.1846. Min Act: -0.0000

Data Index: 335205 (C4 (Web Text))

Max Activating Token Index: 419

Text #2

Max Range: 0.2123. Min Range: -0.2123

Max Act: 0.1745. Min Act: -0.0000

Data Index: 589732 (C4 (Web Text))

Max Activating Token Index: 266

Text #3

Max Range: 0.2123. Min Range: -0.2123

Max Act: 0.1568. Min Act: -0.0000

Data Index: 790120 (C4 (Web Text))

Max Activating Token Index: 972

Text #4

Max Range: 0.2123. Min Range: -0.2123

Max Act: 0.1444. Min Act: -0.0000

Data Index: 1151081 (C4 (Web Text))

Max Activating Token Index: 47

Text #5

Max Range: 0.2123. Min Range: -0.2123

Max Act: 0.1516. Min Act: -0.0000

Data Index: 165401 (C4 (Web Text))

Max Activating Token Index: 222

Text #6

Max Range: 0.2123. Min Range: -0.2123

Max Act: 0.1496. Min Act: -0.0000

Data Index: 895266 (C4 (Web Text))

Max Activating Token Index: 299

Text #7

Max Range: 0.2123. Min Range: -0.2123

Max Act: 0.1465. Min Act: -0.0000

Data Index: 288043 (C4 (Web Text))

Max Activating Token Index: 574

Text #8

Max Range: 0.2123. Min Range: -0.2123

Max Act: 0.1446. Min Act: -0.0000

Data Index: 944140 (C4 (Web Text))

Max Activating Token Index: 805

Text #9

Max Range: 0.2123. Min Range: -0.2123

Max Act: 0.1433. Min Act: -0.0000

Data Index: 784741 (C4 (Web Text))

Max Activating Token Index: 1000

Text #10

Max Range: 0.2123. Min Range: -0.2123

Max Act: 0.1434. Min Act: -0.0000

Data Index: 1151551 (C4 (Web Text))

Max Activating Token Index: 935

Text #11

Max Range: 0.2123. Min Range: -0.2123

Max Act: 0.1341. Min Act: -0.0000

Data Index: 486772 (C4 (Web Text))

Max Activating Token Index: 994

Text #12

Max Range: 0.2123. Min Range: -0.2123

Max Act: 0.1377. Min Act: -0.0000

Data Index: 492422 (C4 (Web Text))

Max Activating Token Index: 935

Text #13

Max Range: 0.2123. Min Range: -0.2123

Max Act: 0.1416. Min Act: -0.0000

Data Index: 907194 (C4 (Web Text))

Max Activating Token Index: 749

Text #14

Max Range: 0.2123. Min Range: -0.2123

Max Act: 0.1367. Min Act: -0.0000

Data Index: 381942 (C4 (Web Text))

Max Activating Token Index: 39

Text #15

Max Range: 0.2123. Min Range: -0.2123

Max Act: 0.1397. Min Act: -0.0000

Data Index: 492845 (C4 (Web Text))

Max Activating Token Index: 956

Text #16

Max Range: 0.2123. Min Range: -0.2123

Max Act: 0.1368. Min Act: -0.0000

Data Index: 842567 (C4 (Web Text))

Max Activating Token Index: 992

Text #17

Max Range: 0.2123. Min Range: -0.2123

Max Act: 0.1392. Min Act: -0.0000

Data Index: 1035590 (C4 (Web Text))

Max Activating Token Index: 497

Text #18

Max Range: 0.2123. Min Range: -0.2123

Max Act: 0.1354. Min Act: -0.0000

Data Index: 436982 (C4 (Web Text))

Max Activating Token Index: 999

Text #19

Max Range: 0.2123. Min Range: -0.2123

Max Act: 0.1347. Min Act: -0.0000

Data Index: 608931 (C4 (Web Text))

Max Activating Token Index: 531