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

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

Neuron 2087 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: 4.1718. Min Range: -4.1718

Max Act: 4.1718. Min Act: -0.0001

Data Index: 579495 (C4 (Web Text))

Max Activating Token Index: 286

Text #1

Max Range: 4.1718. Min Range: -4.1718

Max Act: 3.7613. Min Act: -0.0000

Data Index: 242261 (C4 (Web Text))

Max Activating Token Index: 459

Text #2

Max Range: 4.1718. Min Range: -4.1718

Max Act: 3.5062. Min Act: -0.0001

Data Index: 116273 (C4 (Web Text))

Max Activating Token Index: 273

Text #3

Max Range: 4.1718. Min Range: -4.1718

Max Act: 3.6761. Min Act: -0.0001

Data Index: 100602 (C4 (Web Text))

Max Activating Token Index: 499

Text #4

Max Range: 4.1718. Min Range: -4.1718

Max Act: 3.2687. Min Act: -0.0001

Data Index: 827445 (C4 (Web Text))

Max Activating Token Index: 600

Text #5

Max Range: 4.1718. Min Range: -4.1718

Max Act: 3.1872. Min Act: -0.0000

Data Index: 757391 (C4 (Web Text))

Max Activating Token Index: 280

Text #6

Max Range: 4.1718. Min Range: -4.1718

Max Act: 2.8124. Min Act: -0.0001

Data Index: 514196 (C4 (Web Text))

Max Activating Token Index: 827

Text #7

Max Range: 4.1718. Min Range: -4.1718

Max Act: 2.8883. Min Act: -0.0001

Data Index: 119576 (C4 (Web Text))

Max Activating Token Index: 333

Text #8

Max Range: 4.1718. Min Range: -4.1718

Max Act: 2.6262. Min Act: -0.0001

Data Index: 1121415 (C4 (Web Text))

Max Activating Token Index: 162

Text #9

Max Range: 4.1718. Min Range: -4.1718

Max Act: 2.6740. Min Act: -0.0000

Data Index: 679800 (C4 (Web Text))

Max Activating Token Index: 819

Text #10

Max Range: 4.1718. Min Range: -4.1718

Max Act: 2.6627. Min Act: -0.0001

Data Index: 286550 (C4 (Web Text))

Max Activating Token Index: 527

Text #11

Max Range: 4.1718. Min Range: -4.1718

Max Act: 2.6596. Min Act: -0.0001

Data Index: 1207017 (C4 (Web Text))

Max Activating Token Index: 813

Text #12

Max Range: 4.1718. Min Range: -4.1718

Max Act: 2.6224. Min Act: -0.0001

Data Index: 358818 (C4 (Web Text))

Max Activating Token Index: 523

Text #13

Max Range: 4.1718. Min Range: -4.1718

Max Act: 2.6238. Min Act: -0.0001

Data Index: 150997 (C4 (Web Text))

Max Activating Token Index: 579

Text #14

Max Range: 4.1718. Min Range: -4.1718

Max Act: 2.6121. Min Act: -0.0001

Data Index: 470505 (C4 (Web Text))

Max Activating Token Index: 265

Text #15

Max Range: 4.1718. Min Range: -4.1718

Max Act: 2.5797. Min Act: -0.0001

Data Index: 345622 (C4 (Web Text))

Max Activating Token Index: 816

Text #16

Max Range: 4.1718. Min Range: -4.1718

Max Act: 2.5707. Min Act: -0.0001

Data Index: 1174124 (C4 (Web Text))

Max Activating Token Index: 700

Text #17

Max Range: 4.1718. Min Range: -4.1718

Max Act: 2.4276. Min Act: -0.0000

Data Index: 1062383 (C4 (Web Text))

Max Activating Token Index: 994

Text #18

Max Range: 4.1718. Min Range: -4.1718

Max Act: 2.5406. Min Act: -0.0001

Data Index: 977391 (C4 (Web Text))

Max Activating Token Index: 25

Text #19

Max Range: 4.1718. Min Range: -4.1718

Max Act: 2.2968. Min Act: -0.0000

Data Index: 571028 (C4 (Web Text))

Max Activating Token Index: 316