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

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

Neuron 5988 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: 0.4115. Min Range: -0.4115

Max Act: 0.4115. Min Act: -0.0002

Data Index: 1451045 (Python Code)

Max Activating Token Index: 33

Text #1

Max Range: 0.4115. Min Range: -0.4115

Max Act: 0.3932. Min Act: -0.0002

Data Index: 1500949 (Python Code)

Max Activating Token Index: 67

Text #2

Max Range: 0.4115. Min Range: -0.4115

Max Act: 0.3731. Min Act: -0.0002

Data Index: 1486102 (Python Code)

Max Activating Token Index: 8

Text #3

Max Range: 0.4115. Min Range: -0.4115

Max Act: 0.3673. Min Act: -0.0002

Data Index: 1408262 (Python Code)

Max Activating Token Index: 126

Text #4

Max Range: 0.4115. Min Range: -0.4115

Max Act: 0.3746. Min Act: -0.0002

Data Index: 1593788 (Python Code)

Max Activating Token Index: 24

Text #5

Max Range: 0.4115. Min Range: -0.4115

Max Act: 0.3482. Min Act: -0.0002

Data Index: 1567596 (Python Code)

Max Activating Token Index: 901

Text #6

Max Range: 0.4115. Min Range: -0.4115

Max Act: 0.3524. Min Act: -0.0002

Data Index: 1437803 (Python Code)

Max Activating Token Index: 69

Text #7

Max Range: 0.4115. Min Range: -0.4115

Max Act: 0.3560. Min Act: -0.0002

Data Index: 1635337 (Python Code)

Max Activating Token Index: 375

Text #8

Max Range: 0.4115. Min Range: -0.4115

Max Act: 0.3565. Min Act: -0.0002

Data Index: 1577282 (Python Code)

Max Activating Token Index: 796

Text #9

Max Range: 0.4115. Min Range: -0.4115

Max Act: 0.3497. Min Act: -0.0002

Data Index: 1543819 (Python Code)

Max Activating Token Index: 5

Text #10

Max Range: 0.4115. Min Range: -0.4115

Max Act: 0.3528. Min Act: -0.0002

Data Index: 1453710 (Python Code)

Max Activating Token Index: 6

Text #11

Max Range: 0.4115. Min Range: -0.4115

Max Act: 0.3433. Min Act: -0.0002

Data Index: 1035948 (C4 (Web Text))

Max Activating Token Index: 8

Text #12

Max Range: 0.4115. Min Range: -0.4115

Max Act: 0.3415. Min Act: -0.0002

Data Index: 1593226 (Python Code)

Max Activating Token Index: 43

Text #13

Max Range: 0.4115. Min Range: -0.4115

Max Act: 0.3436. Min Act: -0.0002

Data Index: 1418207 (Python Code)

Max Activating Token Index: 11

Text #14

Max Range: 0.4115. Min Range: -0.4115

Max Act: 0.3384. Min Act: -0.0002

Data Index: 1492283 (Python Code)

Max Activating Token Index: 29

Text #15

Max Range: 0.4115. Min Range: -0.4115

Max Act: 0.3331. Min Act: -0.0002

Data Index: 1390710 (Python Code)

Max Activating Token Index: 20

Text #16

Max Range: 0.4115. Min Range: -0.4115

Max Act: 0.3351. Min Act: -0.0002

Data Index: 1538726 (Python Code)

Max Activating Token Index: 76

Text #17

Max Range: 0.4115. Min Range: -0.4115

Max Act: 0.3231. Min Act: -0.0002

Data Index: 1534856 (Python Code)

Max Activating Token Index: 106

Text #18

Max Range: 0.4115. Min Range: -0.4115

Max Act: 0.3338. Min Act: -0.0002

Data Index: 1507999 (Python Code)

Max Activating Token Index: 125

Text #19

Max Range: 0.4115. Min Range: -0.4115

Max Act: 0.3287. Min Act: -0.0002

Data Index: 1624730 (Python Code)

Max Activating Token Index: 32