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

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

Neuron 5809 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2933. Min Range: -0.2933

Max Act: 0.2922. Min Act: -0.0000

Data Index: 1595620 (Python Code)

Max Activating Token Index: 1005

Text #1

Max Range: 0.2933. Min Range: -0.2933

Max Act: 0.2933. Min Act: 0.0000

Data Index: 1626667 (Python Code)

Max Activating Token Index: 57

Text #2

Max Range: 0.2933. Min Range: -0.2933

Max Act: 0.2776. Min Act: -0.0000

Data Index: 1600092 (Python Code)

Max Activating Token Index: 377

Text #3

Max Range: 0.2933. Min Range: -0.2933

Max Act: 0.2537. Min Act: 0.0000

Data Index: 1514540 (Python Code)

Max Activating Token Index: 187

Text #4

Max Range: 0.2933. Min Range: -0.2933

Max Act: 0.2498. Min Act: -0.0000

Data Index: 1594063 (Python Code)

Max Activating Token Index: 133

Text #5

Max Range: 0.2933. Min Range: -0.2933

Max Act: 0.2482. Min Act: -0.0000

Data Index: 1384012 (Python Code)

Max Activating Token Index: 504

Text #6

Max Range: 0.2933. Min Range: -0.2933

Max Act: 0.2477. Min Act: -0.0000

Data Index: 1415691 (Python Code)

Max Activating Token Index: 714

Text #7

Max Range: 0.2933. Min Range: -0.2933

Max Act: 0.2394. Min Act: -0.0000

Data Index: 1575450 (Python Code)

Max Activating Token Index: 998

Text #8

Max Range: 0.2933. Min Range: -0.2933

Max Act: 0.2424. Min Act: 0.0000

Data Index: 1584713 (Python Code)

Max Activating Token Index: 513

Text #9

Max Range: 0.2933. Min Range: -0.2933

Max Act: 0.2232. Min Act: -0.0000

Data Index: 1530632 (Python Code)

Max Activating Token Index: 887

Text #10

Max Range: 0.2933. Min Range: -0.2933

Max Act: 0.2373. Min Act: -0.0000

Data Index: 1525622 (Python Code)

Max Activating Token Index: 982

Text #11

Max Range: 0.2933. Min Range: -0.2933

Max Act: 0.2385. Min Act: -0.0000

Data Index: 1444314 (Python Code)

Max Activating Token Index: 778

Text #12

Max Range: 0.2933. Min Range: -0.2933

Max Act: 0.2184. Min Act: -0.0000

Data Index: 1395327 (Python Code)

Max Activating Token Index: 860

Text #13

Max Range: 0.2933. Min Range: -0.2933

Max Act: 0.2273. Min Act: -0.0000

Data Index: 1612323 (Python Code)

Max Activating Token Index: 36

Text #14

Max Range: 0.2933. Min Range: -0.2933

Max Act: 0.2344. Min Act: -0.0000

Data Index: 1529132 (Python Code)

Max Activating Token Index: 121

Text #15

Max Range: 0.2933. Min Range: -0.2933

Max Act: 0.2360. Min Act: -0.0000

Data Index: 1594199 (Python Code)

Max Activating Token Index: 906

Text #16

Max Range: 0.2933. Min Range: -0.2933

Max Act: 0.2275. Min Act: -0.0000

Data Index: 1570426 (Python Code)

Max Activating Token Index: 791

Text #17

Max Range: 0.2933. Min Range: -0.2933

Max Act: 0.2256. Min Act: -0.0000

Data Index: 1387520 (Python Code)

Max Activating Token Index: 48

Text #18

Max Range: 0.2933. Min Range: -0.2933

Max Act: 0.2258. Min Act: -0.0000

Data Index: 1424907 (Python Code)

Max Activating Token Index: 1014

Text #19

Max Range: 0.2933. Min Range: -0.2933

Max Act: 0.2336. Min Act: -0.0000

Data Index: 824827 (C4 (Web Text))

Max Activating Token Index: 981