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

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

Neuron 845 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1321. Min Act: -0.0000

Data Index: 747889 (C4 (Web Text))

Max Activating Token Index: 717

Text #1

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1319. Min Act: -0.0000

Data Index: 1352906 (C4 (Web Text))

Max Activating Token Index: 574

Text #2

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1162. Min Act: -0.0000

Data Index: 668095 (C4 (Web Text))

Max Activating Token Index: 304

Text #3

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1133. Min Act: -0.0000

Data Index: 1075051 (C4 (Web Text))

Max Activating Token Index: 399

Text #4

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1119. Min Act: -0.0000

Data Index: 82204 (C4 (Web Text))

Max Activating Token Index: 638

Text #5

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1105. Min Act: -0.0000

Data Index: 708023 (C4 (Web Text))

Max Activating Token Index: 827

Text #6

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1005. Min Act: -0.0000

Data Index: 944676 (C4 (Web Text))

Max Activating Token Index: 901

Text #7

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.1070. Min Act: -0.0000

Data Index: 45514 (C4 (Web Text))

Max Activating Token Index: 266

Text #8

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0927. Min Act: -0.0000

Data Index: 85414 (C4 (Web Text))

Max Activating Token Index: 24

Text #9

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0865. Min Act: -0.0000

Data Index: 159395 (C4 (Web Text))

Max Activating Token Index: 710

Text #10

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0932. Min Act: -0.0000

Data Index: 1059637 (C4 (Web Text))

Max Activating Token Index: 886

Text #11

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0837. Min Act: -0.0000

Data Index: 614164 (C4 (Web Text))

Max Activating Token Index: 885

Text #12

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0852. Min Act: -0.0000

Data Index: 1223202 (C4 (Web Text))

Max Activating Token Index: 928

Text #13

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0812. Min Act: -0.0000

Data Index: 232414 (C4 (Web Text))

Max Activating Token Index: 156

Text #14

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0824. Min Act: -0.0000

Data Index: 1101530 (C4 (Web Text))

Max Activating Token Index: 365

Text #15

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0852. Min Act: -0.0000

Data Index: 373578 (C4 (Web Text))

Max Activating Token Index: 987

Text #16

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0786. Min Act: -0.0000

Data Index: 67202 (C4 (Web Text))

Max Activating Token Index: 370

Text #17

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0753. Min Act: -0.0000

Data Index: 990139 (C4 (Web Text))

Max Activating Token Index: 974

Text #18

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0799. Min Act: -0.0000

Data Index: 1207756 (C4 (Web Text))

Max Activating Token Index: 498

Text #19

Max Range: 0.1321. Min Range: -0.1321

Max Act: 0.0742. Min Act: -0.0000

Data Index: 855881 (C4 (Web Text))

Max Activating Token Index: 809