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

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

Neuron 281 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.8567. Min Act: -0.0002

Data Index: 1642880 (Python Code)

Max Activating Token Index: 817

Text #1

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.8161. Min Act: -0.0002

Data Index: 1488463 (Python Code)

Max Activating Token Index: 785

Text #2

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.7894. Min Act: -0.0002

Data Index: 1613310 (Python Code)

Max Activating Token Index: 832

Text #3

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.7831. Min Act: -0.0002

Data Index: 1378804 (Python Code)

Max Activating Token Index: 821

Text #4

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.7724. Min Act: -0.0002

Data Index: 1584165 (Python Code)

Max Activating Token Index: 492

Text #5

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.7826. Min Act: -0.0002

Data Index: 1642394 (Python Code)

Max Activating Token Index: 131

Text #6

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.7547. Min Act: -0.0002

Data Index: 1644617 (Python Code)

Max Activating Token Index: 989

Text #7

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.7645. Min Act: -0.0002

Data Index: 1570592 (Python Code)

Max Activating Token Index: 796

Text #8

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.7738. Min Act: -0.0002

Data Index: 1413626 (Python Code)

Max Activating Token Index: 937

Text #9

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.7562. Min Act: -0.0002

Data Index: 1535849 (Python Code)

Max Activating Token Index: 785

Text #10

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.7565. Min Act: -0.0002

Data Index: 1381558 (Python Code)

Max Activating Token Index: 155

Text #11

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.7504. Min Act: -0.0002

Data Index: 1653850 (Python Code)

Max Activating Token Index: 707

Text #12

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.7657. Min Act: -0.0002

Data Index: 1649781 (Python Code)

Max Activating Token Index: 555

Text #13

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.7383. Min Act: -0.0002

Data Index: 1532029 (Python Code)

Max Activating Token Index: 13

Text #14

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.7492. Min Act: -0.0002

Data Index: 1486723 (Python Code)

Max Activating Token Index: 832

Text #15

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.7351. Min Act: -0.0002

Data Index: 1434732 (Python Code)

Max Activating Token Index: 565

Text #16

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.7498. Min Act: -0.0002

Data Index: 1645432 (Python Code)

Max Activating Token Index: 48

Text #17

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.7361. Min Act: -0.0002

Data Index: 1548070 (Python Code)

Max Activating Token Index: 215

Text #18

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.7417. Min Act: -0.0002

Data Index: 1369327 (Python Code)

Max Activating Token Index: 1008

Text #19

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.7298. Min Act: -0.0002

Data Index: 1414222 (Python Code)

Max Activating Token Index: 141