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

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

Neuron 2499 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8639. Min Range: -1.8639

Max Act: 1.6841. Min Act: -0.0000

Data Index: 1377741 (Python Code)

Max Activating Token Index: 686

Text #1

Max Range: 1.8639. Min Range: -1.8639

Max Act: 1.8639. Min Act: -0.0000

Data Index: 1487793 (Python Code)

Max Activating Token Index: 743

Text #2

Max Range: 1.8639. Min Range: -1.8639

Max Act: 1.7916. Min Act: -0.0000

Data Index: 1528419 (Python Code)

Max Activating Token Index: 432

Text #3

Max Range: 1.8639. Min Range: -1.8639

Max Act: 1.8419. Min Act: -0.0000

Data Index: 1613916 (Python Code)

Max Activating Token Index: 139

Text #4

Max Range: 1.8639. Min Range: -1.8639

Max Act: 1.6712. Min Act: -0.0000

Data Index: 1636291 (Python Code)

Max Activating Token Index: 354

Text #5

Max Range: 1.8639. Min Range: -1.8639

Max Act: 1.3288. Min Act: -0.0000

Data Index: 1638085 (Python Code)

Max Activating Token Index: 1009

Text #6

Max Range: 1.8639. Min Range: -1.8639

Max Act: 1.4367. Min Act: -0.0000

Data Index: 1530090 (Python Code)

Max Activating Token Index: 256

Text #7

Max Range: 1.8639. Min Range: -1.8639

Max Act: 1.3118. Min Act: -0.0000

Data Index: 1606503 (Python Code)

Max Activating Token Index: 1011

Text #8

Max Range: 1.8639. Min Range: -1.8639

Max Act: 1.4079. Min Act: -0.0000

Data Index: 1514126 (Python Code)

Max Activating Token Index: 325

Text #9

Max Range: 1.8639. Min Range: -1.8639

Max Act: 1.2349. Min Act: -0.0000

Data Index: 1435724 (Python Code)

Max Activating Token Index: 810

Text #10

Max Range: 1.8639. Min Range: -1.8639

Max Act: 1.3353. Min Act: -0.0000

Data Index: 1504508 (Python Code)

Max Activating Token Index: 807

Text #11

Max Range: 1.8639. Min Range: -1.8639

Max Act: 1.1951. Min Act: -0.0000

Data Index: 1526866 (Python Code)

Max Activating Token Index: 1001

Text #12

Max Range: 1.8639. Min Range: -1.8639

Max Act: 1.3665. Min Act: -0.0000

Data Index: 1437333 (Python Code)

Max Activating Token Index: 1004

Text #13

Max Range: 1.8639. Min Range: -1.8639

Max Act: 1.3633. Min Act: -0.0000

Data Index: 1568706 (Python Code)

Max Activating Token Index: 308

Text #14

Max Range: 1.8639. Min Range: -1.8639

Max Act: 1.2200. Min Act: -0.0000

Data Index: 1614116 (Python Code)

Max Activating Token Index: 21

Text #15

Max Range: 1.8639. Min Range: -1.8639

Max Act: 1.3236. Min Act: -0.0000

Data Index: 1416260 (Python Code)

Max Activating Token Index: 111

Text #16

Max Range: 1.8639. Min Range: -1.8639

Max Act: 1.2283. Min Act: -0.0000

Data Index: 1466144 (Python Code)

Max Activating Token Index: 934

Text #17

Max Range: 1.8639. Min Range: -1.8639

Max Act: 1.1774. Min Act: -0.0000

Data Index: 1613856 (Python Code)

Max Activating Token Index: 885

Text #18

Max Range: 1.8639. Min Range: -1.8639

Max Act: 1.1993. Min Act: -0.0000

Data Index: 1581809 (Python Code)

Max Activating Token Index: 225

Text #19

Max Range: 1.8639. Min Range: -1.8639

Max Act: 1.1275. Min Act: -0.0000

Data Index: 1411238 (Python Code)

Max Activating Token Index: 1023