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

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

Neuron 2748 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5815. Min Range: -1.5815

Max Act: 1.5815. Min Act: -0.0000

Data Index: 1486593 (Python Code)

Max Activating Token Index: 961

Text #1

Max Range: 1.5815. Min Range: -1.5815

Max Act: 1.3579. Min Act: -0.0000

Data Index: 788575 (C4 (Web Text))

Max Activating Token Index: 949

Text #2

Max Range: 1.5815. Min Range: -1.5815

Max Act: 1.3332. Min Act: -0.0000

Data Index: 1425648 (Python Code)

Max Activating Token Index: 790

Text #3

Max Range: 1.5815. Min Range: -1.5815

Max Act: 1.4180. Min Act: -0.0000

Data Index: 1428951 (Python Code)

Max Activating Token Index: 130

Text #4

Max Range: 1.5815. Min Range: -1.5815

Max Act: 1.2627. Min Act: -0.0000

Data Index: 1428531 (Python Code)

Max Activating Token Index: 776

Text #5

Max Range: 1.5815. Min Range: -1.5815

Max Act: 1.4252. Min Act: -0.0000

Data Index: 1083953 (C4 (Web Text))

Max Activating Token Index: 106

Text #6

Max Range: 1.5815. Min Range: -1.5815

Max Act: 1.3705. Min Act: -0.0000

Data Index: 1297157 (C4 (Web Text))

Max Activating Token Index: 33

Text #7

Max Range: 1.5815. Min Range: -1.5815

Max Act: 1.1738. Min Act: -0.0000

Data Index: 1109911 (C4 (Web Text))

Max Activating Token Index: 48

Text #8

Max Range: 1.5815. Min Range: -1.5815

Max Act: 1.2348. Min Act: -0.0000

Data Index: 980484 (C4 (Web Text))

Max Activating Token Index: 61

Text #9

Max Range: 1.5815. Min Range: -1.5815

Max Act: 1.2864. Min Act: -0.0000

Data Index: 23913 (C4 (Web Text))

Max Activating Token Index: 992

Text #10

Max Range: 1.5815. Min Range: -1.5815

Max Act: 1.1965. Min Act: -0.0000

Data Index: 1239320 (C4 (Web Text))

Max Activating Token Index: 43

Text #11

Max Range: 1.5815. Min Range: -1.5815

Max Act: 1.2647. Min Act: -0.0000

Data Index: 1135309 (C4 (Web Text))

Max Activating Token Index: 957

Text #12

Max Range: 1.5815. Min Range: -1.5815

Max Act: 1.2635. Min Act: -0.0000

Data Index: 653549 (C4 (Web Text))

Max Activating Token Index: 24

Text #13

Max Range: 1.5815. Min Range: -1.5815

Max Act: 1.1938. Min Act: -0.0000

Data Index: 1286906 (C4 (Web Text))

Max Activating Token Index: 523

Text #14

Max Range: 1.5815. Min Range: -1.5815

Max Act: 1.1554. Min Act: -0.0000

Data Index: 792801 (C4 (Web Text))

Max Activating Token Index: 973

Text #15

Max Range: 1.5815. Min Range: -1.5815

Max Act: 1.2256. Min Act: -0.0000

Data Index: 871487 (C4 (Web Text))

Max Activating Token Index: 780

Text #16

Max Range: 1.5815. Min Range: -1.5815

Max Act: 1.2855. Min Act: -0.0000

Data Index: 419921 (C4 (Web Text))

Max Activating Token Index: 692

Text #17

Max Range: 1.5815. Min Range: -1.5815

Max Act: 1.1894. Min Act: -0.0000

Data Index: 412417 (C4 (Web Text))

Max Activating Token Index: 841

Text #18

Max Range: 1.5815. Min Range: -1.5815

Max Act: 1.2622. Min Act: -0.0000

Data Index: 531536 (C4 (Web Text))

Max Activating Token Index: 223

Text #19

Max Range: 1.5815. Min Range: -1.5815

Max Act: 1.1852. Min Act: -0.0000

Data Index: 125298 (C4 (Web Text))

Max Activating Token Index: 577