Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2860 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.8618. Min Range: -1.8618

Max Act: 1.7344. Min Act: -0.0001

Data Index: 1527132 (Python Code)

Max Activating Token Index: 688

Text #1

Max Range: 1.8618. Min Range: -1.8618

Max Act: 1.7871. Min Act: -0.0001

Data Index: 1425947 (Python Code)

Max Activating Token Index: 611

Text #2

Max Range: 1.8618. Min Range: -1.8618

Max Act: 1.8618. Min Act: -0.0001

Data Index: 1653673 (Python Code)

Max Activating Token Index: 553

Text #3

Max Range: 1.8618. Min Range: -1.8618

Max Act: 1.8082. Min Act: -0.0001

Data Index: 1407473 (Python Code)

Max Activating Token Index: 788

Text #4

Max Range: 1.8618. Min Range: -1.8618

Max Act: 1.7454. Min Act: -0.0001

Data Index: 1542634 (Python Code)

Max Activating Token Index: 688

Text #5

Max Range: 1.8618. Min Range: -1.8618

Max Act: 1.6472. Min Act: -0.0001

Data Index: 1474636 (Python Code)

Max Activating Token Index: 210

Text #6

Max Range: 1.8618. Min Range: -1.8618

Max Act: 1.6705. Min Act: -0.0000

Data Index: 1452479 (Python Code)

Max Activating Token Index: 996

Text #7

Max Range: 1.8618. Min Range: -1.8618

Max Act: 1.6924. Min Act: -0.0001

Data Index: 1561155 (Python Code)

Max Activating Token Index: 703

Text #8

Max Range: 1.8618. Min Range: -1.8618

Max Act: 1.7015. Min Act: -0.0001

Data Index: 1579293 (Python Code)

Max Activating Token Index: 160

Text #9

Max Range: 1.8618. Min Range: -1.8618

Max Act: 1.7386. Min Act: -0.0001

Data Index: 1486116 (Python Code)

Max Activating Token Index: 511

Text #10

Max Range: 1.8618. Min Range: -1.8618

Max Act: 1.6098. Min Act: -0.0001

Data Index: 1608053 (Python Code)

Max Activating Token Index: 528

Text #11

Max Range: 1.8618. Min Range: -1.8618

Max Act: 1.7286. Min Act: -0.0001

Data Index: 1469063 (Python Code)

Max Activating Token Index: 617

Text #12

Max Range: 1.8618. Min Range: -1.8618

Max Act: 1.6813. Min Act: -0.0001

Data Index: 1370797 (Python Code)

Max Activating Token Index: 738

Text #13

Max Range: 1.8618. Min Range: -1.8618

Max Act: 1.6610. Min Act: -0.0001

Data Index: 1611825 (Python Code)

Max Activating Token Index: 435

Text #14

Max Range: 1.8618. Min Range: -1.8618

Max Act: 1.5698. Min Act: -0.0001

Data Index: 1580587 (Python Code)

Max Activating Token Index: 1002

Text #15

Max Range: 1.8618. Min Range: -1.8618

Max Act: 1.5968. Min Act: -0.0001

Data Index: 1435042 (Python Code)

Max Activating Token Index: 281

Text #16

Max Range: 1.8618. Min Range: -1.8618

Max Act: 1.5901. Min Act: -0.0001

Data Index: 1429821 (Python Code)

Max Activating Token Index: 606

Text #17

Max Range: 1.8618. Min Range: -1.8618

Max Act: 1.5218. Min Act: -0.0001

Data Index: 1585188 (Python Code)

Max Activating Token Index: 997

Text #18

Max Range: 1.8618. Min Range: -1.8618

Max Act: 1.5552. Min Act: -0.0001

Data Index: 1608086 (Python Code)

Max Activating Token Index: 114

Text #19

Max Range: 1.8618. Min Range: -1.8618

Max Act: 1.5805. Min Act: -0.0001

Data Index: 1573667 (Python Code)

Max Activating Token Index: 729