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

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

Neuron 2861 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5142. Min Range: -0.5142

Max Act: 0.5142. Min Act: -0.0000

Data Index: 628622 (C4 (Web Text))

Max Activating Token Index: 889

Text #1

Max Range: 0.5142. Min Range: -0.5142

Max Act: 0.5044. Min Act: -0.0000

Data Index: 623526 (C4 (Web Text))

Max Activating Token Index: 540

Text #2

Max Range: 0.5142. Min Range: -0.5142

Max Act: 0.4822. Min Act: -0.0000

Data Index: 1266603 (C4 (Web Text))

Max Activating Token Index: 742

Text #3

Max Range: 0.5142. Min Range: -0.5142

Max Act: 0.5044. Min Act: -0.0000

Data Index: 1001337 (C4 (Web Text))

Max Activating Token Index: 589

Text #4

Max Range: 0.5142. Min Range: -0.5142

Max Act: 0.4950. Min Act: -0.0000

Data Index: 813739 (C4 (Web Text))

Max Activating Token Index: 679

Text #5

Max Range: 0.5142. Min Range: -0.5142

Max Act: 0.5006. Min Act: -0.0000

Data Index: 55009 (C4 (Web Text))

Max Activating Token Index: 809

Text #6

Max Range: 0.5142. Min Range: -0.5142

Max Act: 0.4659. Min Act: -0.0000

Data Index: 1136082 (C4 (Web Text))

Max Activating Token Index: 938

Text #7

Max Range: 0.5142. Min Range: -0.5142

Max Act: 0.4566. Min Act: -0.0000

Data Index: 110522 (C4 (Web Text))

Max Activating Token Index: 886

Text #8

Max Range: 0.5142. Min Range: -0.5142

Max Act: 0.4475. Min Act: -0.0000

Data Index: 586865 (C4 (Web Text))

Max Activating Token Index: 726

Text #9

Max Range: 0.5142. Min Range: -0.5142

Max Act: 0.4522. Min Act: -0.0000

Data Index: 414721 (C4 (Web Text))

Max Activating Token Index: 882

Text #10

Max Range: 0.5142. Min Range: -0.5142

Max Act: 0.4653. Min Act: -0.0000

Data Index: 147899 (C4 (Web Text))

Max Activating Token Index: 995

Text #11

Max Range: 0.5142. Min Range: -0.5142

Max Act: 0.4497. Min Act: -0.0000

Data Index: 554901 (C4 (Web Text))

Max Activating Token Index: 857

Text #12

Max Range: 0.5142. Min Range: -0.5142

Max Act: 0.4871. Min Act: -0.0000

Data Index: 565052 (C4 (Web Text))

Max Activating Token Index: 561

Text #13

Max Range: 0.5142. Min Range: -0.5142

Max Act: 0.4466. Min Act: -0.0000

Data Index: 173756 (C4 (Web Text))

Max Activating Token Index: 653

Text #14

Max Range: 0.5142. Min Range: -0.5142

Max Act: 0.4753. Min Act: -0.0000

Data Index: 810226 (C4 (Web Text))

Max Activating Token Index: 791

Text #15

Max Range: 0.5142. Min Range: -0.5142

Max Act: 0.4543. Min Act: -0.0000

Data Index: 1118351 (C4 (Web Text))

Max Activating Token Index: 307

Text #16

Max Range: 0.5142. Min Range: -0.5142

Max Act: 0.4513. Min Act: -0.0000

Data Index: 264871 (C4 (Web Text))

Max Activating Token Index: 596

Text #17

Max Range: 0.5142. Min Range: -0.5142

Max Act: 0.4391. Min Act: -0.0000

Data Index: 921478 (C4 (Web Text))

Max Activating Token Index: 490

Text #18

Max Range: 0.5142. Min Range: -0.5142

Max Act: 0.4493. Min Act: -0.0000

Data Index: 924331 (C4 (Web Text))

Max Activating Token Index: 811

Text #19

Max Range: 0.5142. Min Range: -0.5142

Max Act: 0.4092. Min Act: -0.0000

Data Index: 1351683 (C4 (Web Text))

Max Activating Token Index: 702