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

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

Neuron 2003 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: 0.9020. Min Range: -0.9020

Max Act: 0.9020. Min Act: -0.0001

Data Index: 639583 (C4 (Web Text))

Max Activating Token Index: 920

Text #1

Max Range: 0.9020. Min Range: -0.9020

Max Act: 0.7130. Min Act: -0.0000

Data Index: 1314385 (C4 (Web Text))

Max Activating Token Index: 962

Text #2

Max Range: 0.9020. Min Range: -0.9020

Max Act: 0.7330. Min Act: -0.0001

Data Index: 961860 (C4 (Web Text))

Max Activating Token Index: 145

Text #3

Max Range: 0.9020. Min Range: -0.9020

Max Act: 0.6972. Min Act: -0.0000

Data Index: 713755 (C4 (Web Text))

Max Activating Token Index: 892

Text #4

Max Range: 0.9020. Min Range: -0.9020

Max Act: 0.6687. Min Act: -0.0001

Data Index: 496183 (C4 (Web Text))

Max Activating Token Index: 938

Text #5

Max Range: 0.9020. Min Range: -0.9020

Max Act: 0.6816. Min Act: -0.0000

Data Index: 214602 (C4 (Web Text))

Max Activating Token Index: 654

Text #6

Max Range: 0.9020. Min Range: -0.9020

Max Act: 0.6784. Min Act: -0.0001

Data Index: 615476 (C4 (Web Text))

Max Activating Token Index: 695

Text #7

Max Range: 0.9020. Min Range: -0.9020

Max Act: 0.6720. Min Act: -0.0000

Data Index: 37340 (C4 (Web Text))

Max Activating Token Index: 543

Text #8

Max Range: 0.9020. Min Range: -0.9020

Max Act: 0.6901. Min Act: -0.0000

Data Index: 528410 (C4 (Web Text))

Max Activating Token Index: 856

Text #9

Max Range: 0.9020. Min Range: -0.9020

Max Act: 0.6658. Min Act: -0.0001

Data Index: 240694 (C4 (Web Text))

Max Activating Token Index: 583

Text #10

Max Range: 0.9020. Min Range: -0.9020

Max Act: 0.6608. Min Act: -0.0000

Data Index: 675815 (C4 (Web Text))

Max Activating Token Index: 141

Text #11

Max Range: 0.9020. Min Range: -0.9020

Max Act: 0.6583. Min Act: -0.0000

Data Index: 849955 (C4 (Web Text))

Max Activating Token Index: 320

Text #12

Max Range: 0.9020. Min Range: -0.9020

Max Act: 0.6591. Min Act: -0.0001

Data Index: 224072 (C4 (Web Text))

Max Activating Token Index: 515

Text #13

Max Range: 0.9020. Min Range: -0.9020

Max Act: 0.6558. Min Act: -0.0000

Data Index: 1216835 (C4 (Web Text))

Max Activating Token Index: 800

Text #14

Max Range: 0.9020. Min Range: -0.9020

Max Act: 0.6576. Min Act: -0.0000

Data Index: 531110 (C4 (Web Text))

Max Activating Token Index: 741

Text #15

Max Range: 0.9020. Min Range: -0.9020

Max Act: 0.6539. Min Act: -0.0000

Data Index: 1298994 (C4 (Web Text))

Max Activating Token Index: 463

Text #16

Max Range: 0.9020. Min Range: -0.9020

Max Act: 0.6698. Min Act: -0.0001

Data Index: 1027269 (C4 (Web Text))

Max Activating Token Index: 786

Text #17

Max Range: 0.9020. Min Range: -0.9020

Max Act: 0.6460. Min Act: -0.0000

Data Index: 235853 (C4 (Web Text))

Max Activating Token Index: 189

Text #18

Max Range: 0.9020. Min Range: -0.9020

Max Act: 0.6417. Min Act: -0.0000

Data Index: 449539 (C4 (Web Text))

Max Activating Token Index: 443

Text #19

Max Range: 0.9020. Min Range: -0.9020

Max Act: 0.6381. Min Act: -0.0001

Data Index: 281267 (C4 (Web Text))

Max Activating Token Index: 109