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

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

Neuron 2987 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8789. Min Range: -2.8789

Max Act: 2.8789. Min Act: -0.0001

Data Index: 783189 (C4 (Web Text))

Max Activating Token Index: 345

Text #1

Max Range: 2.8789. Min Range: -2.8789

Max Act: 2.8515. Min Act: -0.0000

Data Index: 1114776 (C4 (Web Text))

Max Activating Token Index: 485

Text #2

Max Range: 2.8789. Min Range: -2.8789

Max Act: 2.5973. Min Act: -0.0000

Data Index: 905612 (C4 (Web Text))

Max Activating Token Index: 203

Text #3

Max Range: 2.8789. Min Range: -2.8789

Max Act: 2.6325. Min Act: -0.0000

Data Index: 665357 (C4 (Web Text))

Max Activating Token Index: 289

Text #4

Max Range: 2.8789. Min Range: -2.8789

Max Act: 2.2019. Min Act: -0.0001

Data Index: 1142133 (C4 (Web Text))

Max Activating Token Index: 988

Text #5

Max Range: 2.8789. Min Range: -2.8789

Max Act: 1.9389. Min Act: -0.0000

Data Index: 1144495 (C4 (Web Text))

Max Activating Token Index: 644

Text #6

Max Range: 2.8789. Min Range: -2.8789

Max Act: 2.2184. Min Act: -0.0000

Data Index: 145564 (C4 (Web Text))

Max Activating Token Index: 898

Text #7

Max Range: 2.8789. Min Range: -2.8789

Max Act: 1.8583. Min Act: -0.0000

Data Index: 296331 (C4 (Web Text))

Max Activating Token Index: 131

Text #8

Max Range: 2.8789. Min Range: -2.8789

Max Act: 1.8581. Min Act: -0.0001

Data Index: 1025775 (C4 (Web Text))

Max Activating Token Index: 239

Text #9

Max Range: 2.8789. Min Range: -2.8789

Max Act: 1.9426. Min Act: -0.0001

Data Index: 664817 (C4 (Web Text))

Max Activating Token Index: 976

Text #10

Max Range: 2.8789. Min Range: -2.8789

Max Act: 1.5858. Min Act: -0.0000

Data Index: 385634 (C4 (Web Text))

Max Activating Token Index: 605

Text #11

Max Range: 2.8789. Min Range: -2.8789

Max Act: 1.9756. Min Act: -0.0001

Data Index: 1435953 (Python Code)

Max Activating Token Index: 543

Text #12

Max Range: 2.8789. Min Range: -2.8789

Max Act: 1.8606. Min Act: -0.0001

Data Index: 803464 (C4 (Web Text))

Max Activating Token Index: 485

Text #13

Max Range: 2.8789. Min Range: -2.8789

Max Act: 1.9921. Min Act: -0.0000

Data Index: 273030 (C4 (Web Text))

Max Activating Token Index: 896

Text #14

Max Range: 2.8789. Min Range: -2.8789

Max Act: 1.8879. Min Act: -0.0000

Data Index: 444811 (C4 (Web Text))

Max Activating Token Index: 536

Text #15

Max Range: 2.8789. Min Range: -2.8789

Max Act: 1.8634. Min Act: -0.0000

Data Index: 1063022 (C4 (Web Text))

Max Activating Token Index: 654

Text #16

Max Range: 2.8789. Min Range: -2.8789

Max Act: 1.7557. Min Act: -0.0000

Data Index: 431543 (C4 (Web Text))

Max Activating Token Index: 575

Text #17

Max Range: 2.8789. Min Range: -2.8789

Max Act: 1.7502. Min Act: -0.0001

Data Index: 885388 (C4 (Web Text))

Max Activating Token Index: 765

Text #18

Max Range: 2.8789. Min Range: -2.8789

Max Act: 1.6483. Min Act: -0.0001

Data Index: 904560 (C4 (Web Text))

Max Activating Token Index: 849

Text #19

Max Range: 2.8789. Min Range: -2.8789

Max Act: 1.6784. Min Act: -0.0001

Data Index: 779988 (C4 (Web Text))

Max Activating Token Index: 145