Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2134 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.1592. Min Range: -1.1592

Max Act: 1.1592. Min Act: -0.0000

Data Index: 650751 (C4 (Web Text))

Max Activating Token Index: 376

Text #1

Max Range: 1.1592. Min Range: -1.1592

Max Act: 1.0507. Min Act: -0.0000

Data Index: 1403073 (Python Code)

Max Activating Token Index: 226

Text #2

Max Range: 1.1592. Min Range: -1.1592

Max Act: 1.0749. Min Act: -0.0000

Data Index: 1371263 (Python Code)

Max Activating Token Index: 72

Text #3

Max Range: 1.1592. Min Range: -1.1592

Max Act: 1.0540. Min Act: -0.0000

Data Index: 1504460 (Python Code)

Max Activating Token Index: 228

Text #4

Max Range: 1.1592. Min Range: -1.1592

Max Act: 0.9473. Min Act: -0.0000

Data Index: 1586612 (Python Code)

Max Activating Token Index: 907

Text #5

Max Range: 1.1592. Min Range: -1.1592

Max Act: 1.0215. Min Act: -0.0000

Data Index: 1621059 (Python Code)

Max Activating Token Index: 710

Text #6

Max Range: 1.1592. Min Range: -1.1592

Max Act: 0.9276. Min Act: -0.0000

Data Index: 1366223 (Python Code)

Max Activating Token Index: 74

Text #7

Max Range: 1.1592. Min Range: -1.1592

Max Act: 0.9707. Min Act: -0.0000

Data Index: 1547088 (Python Code)

Max Activating Token Index: 811

Text #8

Max Range: 1.1592. Min Range: -1.1592

Max Act: 0.9019. Min Act: -0.0000

Data Index: 454792 (C4 (Web Text))

Max Activating Token Index: 61

Text #9

Max Range: 1.1592. Min Range: -1.1592

Max Act: 0.8250. Min Act: -0.0000

Data Index: 1606474 (Python Code)

Max Activating Token Index: 749

Text #10

Max Range: 1.1592. Min Range: -1.1592

Max Act: 0.9055. Min Act: -0.0000

Data Index: 106904 (C4 (Web Text))

Max Activating Token Index: 681

Text #11

Max Range: 1.1592. Min Range: -1.1592

Max Act: 0.8697. Min Act: -0.0000

Data Index: 1530550 (Python Code)

Max Activating Token Index: 530

Text #12

Max Range: 1.1592. Min Range: -1.1592

Max Act: 0.8735. Min Act: -0.0000

Data Index: 523068 (C4 (Web Text))

Max Activating Token Index: 90

Text #13

Max Range: 1.1592. Min Range: -1.1592

Max Act: 0.8818. Min Act: -0.0000

Data Index: 174108 (C4 (Web Text))

Max Activating Token Index: 1019

Text #14

Max Range: 1.1592. Min Range: -1.1592

Max Act: 0.8479. Min Act: -0.0000

Data Index: 1539006 (Python Code)

Max Activating Token Index: 42

Text #15

Max Range: 1.1592. Min Range: -1.1592

Max Act: 0.8155. Min Act: -0.0000

Data Index: 1191717 (C4 (Web Text))

Max Activating Token Index: 663

Text #16

Max Range: 1.1592. Min Range: -1.1592

Max Act: 0.8336. Min Act: -0.0000

Data Index: 379827 (C4 (Web Text))

Max Activating Token Index: 1008

Text #17

Max Range: 1.1592. Min Range: -1.1592

Max Act: 0.8359. Min Act: -0.0000

Data Index: 565690 (C4 (Web Text))

Max Activating Token Index: 47

Text #18

Max Range: 1.1592. Min Range: -1.1592

Max Act: 0.8671. Min Act: -0.0000

Data Index: 374227 (C4 (Web Text))

Max Activating Token Index: 242

Text #19

Max Range: 1.1592. Min Range: -1.1592

Max Act: 0.8572. Min Act: -0.0000

Data Index: 1441188 (Python Code)

Max Activating Token Index: 209