Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3183 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.5169. Min Act: -0.0001

Data Index: 1505105 (Python Code)

Max Activating Token Index: 571

Text #1

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.4306. Min Act: -0.0001

Data Index: 1485521 (Python Code)

Max Activating Token Index: 463

Text #2

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.4412. Min Act: -0.0001

Data Index: 1619633 (Python Code)

Max Activating Token Index: 578

Text #3

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3945. Min Act: -0.0001

Data Index: 1546896 (Python Code)

Max Activating Token Index: 914

Text #4

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.4013. Min Act: -0.0001

Data Index: 1429573 (Python Code)

Max Activating Token Index: 701

Text #5

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3663. Min Act: -0.0001

Data Index: 1452922 (Python Code)

Max Activating Token Index: 973

Text #6

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3558. Min Act: -0.0001

Data Index: 1576221 (Python Code)

Max Activating Token Index: 12

Text #7

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3427. Min Act: -0.0001

Data Index: 1476921 (Python Code)

Max Activating Token Index: 369

Text #8

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3758. Min Act: -0.0001

Data Index: 1547669 (Python Code)

Max Activating Token Index: 833

Text #9

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3416. Min Act: -0.0000

Data Index: 1511244 (Python Code)

Max Activating Token Index: 104

Text #10

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3388. Min Act: -0.0000

Data Index: 1276522 (C4 (Web Text))

Max Activating Token Index: 39

Text #11

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3325. Min Act: -0.0001

Data Index: 1399795 (Python Code)

Max Activating Token Index: 567

Text #12

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3447. Min Act: -0.0001

Data Index: 1620973 (Python Code)

Max Activating Token Index: 324

Text #13

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3696. Min Act: -0.0001

Data Index: 1656026 (Python Code)

Max Activating Token Index: 798

Text #14

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3275. Min Act: -0.0001

Data Index: 1465371 (Python Code)

Max Activating Token Index: 456

Text #15

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3168. Min Act: -0.0001

Data Index: 1555445 (Python Code)

Max Activating Token Index: 428

Text #16

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3424. Min Act: -0.0001

Data Index: 1522941 (Python Code)

Max Activating Token Index: 493

Text #17

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3223. Min Act: -0.0000

Data Index: 119193 (C4 (Web Text))

Max Activating Token Index: 48

Text #18

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3109. Min Act: -0.0001

Data Index: 1499812 (Python Code)

Max Activating Token Index: 132

Text #19

Max Range: 0.5169. Min Range: -0.5169

Max Act: 0.3175. Min Act: -0.0001

Data Index: 1434390 (Python Code)

Max Activating Token Index: 162