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

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

Neuron 2518 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.8867. Min Act: -0.0000

Data Index: 1496128 (Python Code)

Max Activating Token Index: 487

Text #1

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.8636. Min Act: -0.0001

Data Index: 1375263 (Python Code)

Max Activating Token Index: 540

Text #2

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.7665. Min Act: -0.0001

Data Index: 1465934 (Python Code)

Max Activating Token Index: 775

Text #3

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.8327. Min Act: -0.0001

Data Index: 1590819 (Python Code)

Max Activating Token Index: 934

Text #4

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.8242. Min Act: -0.0001

Data Index: 1471014 (Python Code)

Max Activating Token Index: 136

Text #5

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.8493. Min Act: -0.0001

Data Index: 1405865 (Python Code)

Max Activating Token Index: 844

Text #6

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.8467. Min Act: -0.0000

Data Index: 1516115 (Python Code)

Max Activating Token Index: 124

Text #7

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.8006. Min Act: -0.0000

Data Index: 1483370 (Python Code)

Max Activating Token Index: 871

Text #8

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.8098. Min Act: -0.0001

Data Index: 1490035 (Python Code)

Max Activating Token Index: 627

Text #9

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.8524. Min Act: -0.0001

Data Index: 1510222 (Python Code)

Max Activating Token Index: 728

Text #10

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.7594. Min Act: -0.0001

Data Index: 1461738 (Python Code)

Max Activating Token Index: 252

Text #11

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.7786. Min Act: -0.0001

Data Index: 1535629 (Python Code)

Max Activating Token Index: 394

Text #12

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.7145. Min Act: -0.0001

Data Index: 1628419 (Python Code)

Max Activating Token Index: 866

Text #13

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.8190. Min Act: -0.0000

Data Index: 1602055 (Python Code)

Max Activating Token Index: 981

Text #14

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.7884. Min Act: -0.0001

Data Index: 1594850 (Python Code)

Max Activating Token Index: 956

Text #15

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.7573. Min Act: -0.0001

Data Index: 1547624 (Python Code)

Max Activating Token Index: 671

Text #16

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.7615. Min Act: -0.0001

Data Index: 1622870 (Python Code)

Max Activating Token Index: 939

Text #17

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.7111. Min Act: -0.0001

Data Index: 1637163 (Python Code)

Max Activating Token Index: 398

Text #18

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.6888. Min Act: -0.0001

Data Index: 1580316 (Python Code)

Max Activating Token Index: 629

Text #19

Max Range: 0.8867. Min Range: -0.8867

Max Act: 0.7442. Min Act: -0.0001

Data Index: 1442957 (Python Code)

Max Activating Token Index: 746