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

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

Neuron 538 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7863. Min Range: -1.7863

Max Act: 1.7863. Min Act: -0.0000

Data Index: 904320 (C4 (Web Text))

Max Activating Token Index: 739

Text #1

Max Range: 1.7863. Min Range: -1.7863

Max Act: 1.5584. Min Act: -0.0000

Data Index: 182676 (C4 (Web Text))

Max Activating Token Index: 16

Text #2

Max Range: 1.7863. Min Range: -1.7863

Max Act: 1.5824. Min Act: -0.0000

Data Index: 623938 (C4 (Web Text))

Max Activating Token Index: 366

Text #3

Max Range: 1.7863. Min Range: -1.7863

Max Act: 1.4098. Min Act: -0.0000

Data Index: 257987 (C4 (Web Text))

Max Activating Token Index: 538

Text #4

Max Range: 1.7863. Min Range: -1.7863

Max Act: 1.4618. Min Act: -0.0000

Data Index: 139353 (C4 (Web Text))

Max Activating Token Index: 19

Text #5

Max Range: 1.7863. Min Range: -1.7863

Max Act: 1.3816. Min Act: -0.0000

Data Index: 742081 (C4 (Web Text))

Max Activating Token Index: 21

Text #6

Max Range: 1.7863. Min Range: -1.7863

Max Act: 1.3590. Min Act: -0.0000

Data Index: 361987 (C4 (Web Text))

Max Activating Token Index: 472

Text #7

Max Range: 1.7863. Min Range: -1.7863

Max Act: 1.4125. Min Act: -0.0000

Data Index: 80084 (C4 (Web Text))

Max Activating Token Index: 612

Text #8

Max Range: 1.7863. Min Range: -1.7863

Max Act: 1.3590. Min Act: -0.0000

Data Index: 127132 (C4 (Web Text))

Max Activating Token Index: 100

Text #9

Max Range: 1.7863. Min Range: -1.7863

Max Act: 1.3488. Min Act: -0.0000

Data Index: 1062175 (C4 (Web Text))

Max Activating Token Index: 164

Text #10

Max Range: 1.7863. Min Range: -1.7863

Max Act: 1.4489. Min Act: -0.0000

Data Index: 64971 (C4 (Web Text))

Max Activating Token Index: 316

Text #11

Max Range: 1.7863. Min Range: -1.7863

Max Act: 1.4068. Min Act: -0.0000

Data Index: 650603 (C4 (Web Text))

Max Activating Token Index: 881

Text #12

Max Range: 1.7863. Min Range: -1.7863

Max Act: 1.3043. Min Act: -0.0000

Data Index: 1337028 (C4 (Web Text))

Max Activating Token Index: 47

Text #13

Max Range: 1.7863. Min Range: -1.7863

Max Act: 1.2563. Min Act: -0.0000

Data Index: 1159678 (C4 (Web Text))

Max Activating Token Index: 217

Text #14

Max Range: 1.7863. Min Range: -1.7863

Max Act: 1.3127. Min Act: -0.0000

Data Index: 645928 (C4 (Web Text))

Max Activating Token Index: 793

Text #15

Max Range: 1.7863. Min Range: -1.7863

Max Act: 1.2713. Min Act: -0.0000

Data Index: 589695 (C4 (Web Text))

Max Activating Token Index: 403

Text #16

Max Range: 1.7863. Min Range: -1.7863

Max Act: 1.2199. Min Act: -0.0000

Data Index: 1135160 (C4 (Web Text))

Max Activating Token Index: 344

Text #17

Max Range: 1.7863. Min Range: -1.7863

Max Act: 1.2512. Min Act: -0.0000

Data Index: 466152 (C4 (Web Text))

Max Activating Token Index: 614

Text #18

Max Range: 1.7863. Min Range: -1.7863

Max Act: 1.2700. Min Act: -0.0000

Data Index: 1304487 (C4 (Web Text))

Max Activating Token Index: 582

Text #19

Max Range: 1.7863. Min Range: -1.7863

Max Act: 1.1637. Min Act: -0.0000

Data Index: 1339213 (C4 (Web Text))

Max Activating Token Index: 760