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

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

Neuron 2983 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: 1.8987. Min Range: -1.8987

Max Act: 1.8987. Min Act: -0.0002

Data Index: 1414294 (Python Code)

Max Activating Token Index: 712

Text #1

Max Range: 1.8987. Min Range: -1.8987

Max Act: 1.8898. Min Act: -0.0002

Data Index: 1503163 (Python Code)

Max Activating Token Index: 247

Text #2

Max Range: 1.8987. Min Range: -1.8987

Max Act: 1.8597. Min Act: -0.0002

Data Index: 1384061 (Python Code)

Max Activating Token Index: 760

Text #3

Max Range: 1.8987. Min Range: -1.8987

Max Act: 1.8679. Min Act: -0.0002

Data Index: 1522231 (Python Code)

Max Activating Token Index: 829

Text #4

Max Range: 1.8987. Min Range: -1.8987

Max Act: 1.8874. Min Act: -0.0002

Data Index: 1568930 (Python Code)

Max Activating Token Index: 961

Text #5

Max Range: 1.8987. Min Range: -1.8987

Max Act: 1.8623. Min Act: -0.0002

Data Index: 1377030 (Python Code)

Max Activating Token Index: 505

Text #6

Max Range: 1.8987. Min Range: -1.8987

Max Act: 1.8678. Min Act: -0.0002

Data Index: 1609773 (Python Code)

Max Activating Token Index: 693

Text #7

Max Range: 1.8987. Min Range: -1.8987

Max Act: 1.8008. Min Act: -0.0002

Data Index: 1643853 (Python Code)

Max Activating Token Index: 743

Text #8

Max Range: 1.8987. Min Range: -1.8987

Max Act: 1.8727. Min Act: -0.0002

Data Index: 1486900 (Python Code)

Max Activating Token Index: 776

Text #9

Max Range: 1.8987. Min Range: -1.8987

Max Act: 1.8390. Min Act: -0.0002

Data Index: 1645413 (Python Code)

Max Activating Token Index: 775

Text #10

Max Range: 1.8987. Min Range: -1.8987

Max Act: 1.7880. Min Act: -0.0002

Data Index: 1389077 (Python Code)

Max Activating Token Index: 739

Text #11

Max Range: 1.8987. Min Range: -1.8987

Max Act: 1.8312. Min Act: -0.0002

Data Index: 1464724 (Python Code)

Max Activating Token Index: 29

Text #12

Max Range: 1.8987. Min Range: -1.8987

Max Act: 1.8064. Min Act: -0.0002

Data Index: 1575336 (Python Code)

Max Activating Token Index: 449

Text #13

Max Range: 1.8987. Min Range: -1.8987

Max Act: 1.7645. Min Act: -0.0002

Data Index: 1499798 (Python Code)

Max Activating Token Index: 691

Text #14

Max Range: 1.8987. Min Range: -1.8987

Max Act: 1.7654. Min Act: -0.0002

Data Index: 1540145 (Python Code)

Max Activating Token Index: 543

Text #15

Max Range: 1.8987. Min Range: -1.8987

Max Act: 1.7887. Min Act: -0.0002

Data Index: 1408881 (Python Code)

Max Activating Token Index: 890

Text #16

Max Range: 1.8987. Min Range: -1.8987

Max Act: 1.7452. Min Act: -0.0002

Data Index: 1545200 (Python Code)

Max Activating Token Index: 791

Text #17

Max Range: 1.8987. Min Range: -1.8987

Max Act: 1.7440. Min Act: -0.0002

Data Index: 1395036 (Python Code)

Max Activating Token Index: 554

Text #18

Max Range: 1.8987. Min Range: -1.8987

Max Act: 1.7820. Min Act: -0.0002

Data Index: 1367247 (Python Code)

Max Activating Token Index: 660

Text #19

Max Range: 1.8987. Min Range: -1.8987

Max Act: 1.7615. Min Act: -0.0002

Data Index: 1367032 (Python Code)

Max Activating Token Index: 22