Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1603 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8631. Min Range: -0.8631

Max Act: 0.8631. Min Act: -0.0001

Data Index: 1611425 (Python Code)

Max Activating Token Index: 339

Text #1

Max Range: 0.8631. Min Range: -0.8631

Max Act: 0.8046. Min Act: -0.0001

Data Index: 1395657 (Python Code)

Max Activating Token Index: 661

Text #2

Max Range: 0.8631. Min Range: -0.8631

Max Act: 0.7504. Min Act: -0.0001

Data Index: 1606571 (Python Code)

Max Activating Token Index: 418

Text #3

Max Range: 0.8631. Min Range: -0.8631

Max Act: 0.7596. Min Act: -0.0001

Data Index: 1423510 (Python Code)

Max Activating Token Index: 45

Text #4

Max Range: 0.8631. Min Range: -0.8631

Max Act: 0.6855. Min Act: -0.0001

Data Index: 1622679 (Python Code)

Max Activating Token Index: 258

Text #5

Max Range: 0.8631. Min Range: -0.8631

Max Act: 0.6685. Min Act: -0.0001

Data Index: 1424791 (Python Code)

Max Activating Token Index: 651

Text #6

Max Range: 0.8631. Min Range: -0.8631

Max Act: 0.6686. Min Act: -0.0001

Data Index: 1621220 (Python Code)

Max Activating Token Index: 255

Text #7

Max Range: 0.8631. Min Range: -0.8631

Max Act: 0.7119. Min Act: -0.0001

Data Index: 1386845 (Python Code)

Max Activating Token Index: 702

Text #8

Max Range: 0.8631. Min Range: -0.8631

Max Act: 0.6753. Min Act: -0.0001

Data Index: 1494045 (Python Code)

Max Activating Token Index: 912

Text #9

Max Range: 0.8631. Min Range: -0.8631

Max Act: 0.6533. Min Act: -0.0001

Data Index: 1415230 (Python Code)

Max Activating Token Index: 86

Text #10

Max Range: 0.8631. Min Range: -0.8631

Max Act: 0.6681. Min Act: -0.0001

Data Index: 1446585 (Python Code)

Max Activating Token Index: 67

Text #11

Max Range: 0.8631. Min Range: -0.8631

Max Act: 0.7130. Min Act: -0.0001

Data Index: 1476995 (Python Code)

Max Activating Token Index: 135

Text #12

Max Range: 0.8631. Min Range: -0.8631

Max Act: 0.6481. Min Act: -0.0001

Data Index: 1473001 (Python Code)

Max Activating Token Index: 960

Text #13

Max Range: 0.8631. Min Range: -0.8631

Max Act: 0.6832. Min Act: -0.0001

Data Index: 1411296 (Python Code)

Max Activating Token Index: 24

Text #14

Max Range: 0.8631. Min Range: -0.8631

Max Act: 0.6602. Min Act: -0.0001

Data Index: 1391384 (Python Code)

Max Activating Token Index: 960

Text #15

Max Range: 0.8631. Min Range: -0.8631

Max Act: 0.6607. Min Act: -0.0001

Data Index: 1395496 (Python Code)

Max Activating Token Index: 933

Text #16

Max Range: 0.8631. Min Range: -0.8631

Max Act: 0.6767. Min Act: -0.0001

Data Index: 1646979 (Python Code)

Max Activating Token Index: 119

Text #17

Max Range: 0.8631. Min Range: -0.8631

Max Act: 0.6375. Min Act: -0.0001

Data Index: 1375731 (Python Code)

Max Activating Token Index: 224

Text #18

Max Range: 0.8631. Min Range: -0.8631

Max Act: 0.6763. Min Act: -0.0001

Data Index: 1382449 (Python Code)

Max Activating Token Index: 29

Text #19

Max Range: 0.8631. Min Range: -0.8631

Max Act: 0.6724. Min Act: -0.0001

Data Index: 1534137 (Python Code)

Max Activating Token Index: 217