Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3866 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.1164. Min Act: -0.0000

Data Index: 171604 (C4 (Web Text))

Max Activating Token Index: 1000

Text #1

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0988. Min Act: -0.0000

Data Index: 542827 (C4 (Web Text))

Max Activating Token Index: 475

Text #2

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0812. Min Act: -0.0000

Data Index: 321178 (C4 (Web Text))

Max Activating Token Index: 458

Text #3

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0772. Min Act: -0.0000

Data Index: 994416 (C4 (Web Text))

Max Activating Token Index: 424

Text #4

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0807. Min Act: -0.0000

Data Index: 324362 (C4 (Web Text))

Max Activating Token Index: 258

Text #5

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0753. Min Act: -0.0000

Data Index: 528383 (C4 (Web Text))

Max Activating Token Index: 978

Text #6

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0706. Min Act: -0.0000

Data Index: 880252 (C4 (Web Text))

Max Activating Token Index: 640

Text #7

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0717. Min Act: -0.0000

Data Index: 1438656 (Python Code)

Max Activating Token Index: 545

Text #8

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0690. Min Act: -0.0000

Data Index: 308100 (C4 (Web Text))

Max Activating Token Index: 860

Text #9

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0650. Min Act: -0.0000

Data Index: 23635 (C4 (Web Text))

Max Activating Token Index: 800

Text #10

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0701. Min Act: -0.0000

Data Index: 1254310 (C4 (Web Text))

Max Activating Token Index: 613

Text #11

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0722. Min Act: -0.0000

Data Index: 254047 (C4 (Web Text))

Max Activating Token Index: 874

Text #12

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0713. Min Act: -0.0000

Data Index: 1474556 (Python Code)

Max Activating Token Index: 977

Text #13

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0722. Min Act: -0.0000

Data Index: 99608 (C4 (Web Text))

Max Activating Token Index: 470

Text #14

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0717. Min Act: -0.0000

Data Index: 66074 (C4 (Web Text))

Max Activating Token Index: 892

Text #15

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0691. Min Act: -0.0000

Data Index: 1149469 (C4 (Web Text))

Max Activating Token Index: 578

Text #16

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0690. Min Act: -0.0000

Data Index: 1562824 (Python Code)

Max Activating Token Index: 423

Text #17

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0685. Min Act: -0.0000

Data Index: 1066001 (C4 (Web Text))

Max Activating Token Index: 318

Text #18

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0650. Min Act: -0.0000

Data Index: 1195647 (C4 (Web Text))

Max Activating Token Index: 566

Text #19

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0666. Min Act: -0.0000

Data Index: 119697 (C4 (Web Text))

Max Activating Token Index: 779