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

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

Neuron 4576 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5579. Min Range: -0.5579

Max Act: 0.5110. Min Act: -0.0001

Data Index: 164083 (C4 (Web Text))

Max Activating Token Index: 955

Text #1

Max Range: 0.5579. Min Range: -0.5579

Max Act: 0.5579. Min Act: -0.0000

Data Index: 840926 (C4 (Web Text))

Max Activating Token Index: 768

Text #2

Max Range: 0.5579. Min Range: -0.5579

Max Act: 0.4874. Min Act: -0.0000

Data Index: 446836 (C4 (Web Text))

Max Activating Token Index: 180

Text #3

Max Range: 0.5579. Min Range: -0.5579

Max Act: 0.5442. Min Act: -0.0000

Data Index: 766202 (C4 (Web Text))

Max Activating Token Index: 858

Text #4

Max Range: 0.5579. Min Range: -0.5579

Max Act: 0.4911. Min Act: -0.0000

Data Index: 905055 (C4 (Web Text))

Max Activating Token Index: 20

Text #5

Max Range: 0.5579. Min Range: -0.5579

Max Act: 0.4563. Min Act: -0.0001

Data Index: 1061994 (C4 (Web Text))

Max Activating Token Index: 981

Text #6

Max Range: 0.5579. Min Range: -0.5579

Max Act: 0.5041. Min Act: -0.0001

Data Index: 1001075 (C4 (Web Text))

Max Activating Token Index: 974

Text #7

Max Range: 0.5579. Min Range: -0.5579

Max Act: 0.5001. Min Act: -0.0000

Data Index: 823063 (C4 (Web Text))

Max Activating Token Index: 448

Text #8

Max Range: 0.5579. Min Range: -0.5579

Max Act: 0.5080. Min Act: -0.0000

Data Index: 119955 (C4 (Web Text))

Max Activating Token Index: 155

Text #9

Max Range: 0.5579. Min Range: -0.5579

Max Act: 0.4876. Min Act: -0.0000

Data Index: 713480 (C4 (Web Text))

Max Activating Token Index: 689

Text #10

Max Range: 0.5579. Min Range: -0.5579

Max Act: 0.5108. Min Act: -0.0001

Data Index: 795652 (C4 (Web Text))

Max Activating Token Index: 915

Text #11

Max Range: 0.5579. Min Range: -0.5579

Max Act: 0.4771. Min Act: -0.0000

Data Index: 284613 (C4 (Web Text))

Max Activating Token Index: 412

Text #12

Max Range: 0.5579. Min Range: -0.5579

Max Act: 0.5183. Min Act: -0.0000

Data Index: 739487 (C4 (Web Text))

Max Activating Token Index: 756

Text #13

Max Range: 0.5579. Min Range: -0.5579

Max Act: 0.4704. Min Act: -0.0000

Data Index: 337599 (C4 (Web Text))

Max Activating Token Index: 681

Text #14

Max Range: 0.5579. Min Range: -0.5579

Max Act: 0.4431. Min Act: -0.0000

Data Index: 828190 (C4 (Web Text))

Max Activating Token Index: 823

Text #15

Max Range: 0.5579. Min Range: -0.5579

Max Act: 0.4572. Min Act: -0.0000

Data Index: 347495 (C4 (Web Text))

Max Activating Token Index: 245

Text #16

Max Range: 0.5579. Min Range: -0.5579

Max Act: 0.4277. Min Act: -0.0000

Data Index: 925561 (C4 (Web Text))

Max Activating Token Index: 145

Text #17

Max Range: 0.5579. Min Range: -0.5579

Max Act: 0.4400. Min Act: -0.0000

Data Index: 784193 (C4 (Web Text))

Max Activating Token Index: 396

Text #18

Max Range: 0.5579. Min Range: -0.5579

Max Act: 0.4776. Min Act: -0.0000

Data Index: 683738 (C4 (Web Text))

Max Activating Token Index: 236

Text #19

Max Range: 0.5579. Min Range: -0.5579

Max Act: 0.4317. Min Act: -0.0000

Data Index: 1179955 (C4 (Web Text))

Max Activating Token Index: 72