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

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

Neuron 8 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5987. Min Range: -1.5987

Max Act: 1.5987. Min Act: -0.0000

Data Index: 26916 (C4 (Web Text))

Max Activating Token Index: 437

Text #1

Max Range: 1.5987. Min Range: -1.5987

Max Act: 0.8614. Min Act: -0.0000

Data Index: 23152 (C4 (Web Text))

Max Activating Token Index: 188

Text #2

Max Range: 1.5987. Min Range: -1.5987

Max Act: 0.7164. Min Act: -0.0000

Data Index: 377267 (C4 (Web Text))

Max Activating Token Index: 689

Text #3

Max Range: 1.5987. Min Range: -1.5987

Max Act: 0.7316. Min Act: -0.0000

Data Index: 938624 (C4 (Web Text))

Max Activating Token Index: 15

Text #4

Max Range: 1.5987. Min Range: -1.5987

Max Act: 0.6600. Min Act: -0.0000

Data Index: 388068 (C4 (Web Text))

Max Activating Token Index: 785

Text #5

Max Range: 1.5987. Min Range: -1.5987

Max Act: 0.6654. Min Act: -0.0000

Data Index: 101890 (C4 (Web Text))

Max Activating Token Index: 55

Text #6

Max Range: 1.5987. Min Range: -1.5987

Max Act: 0.6392. Min Act: -0.0000

Data Index: 559749 (C4 (Web Text))

Max Activating Token Index: 554

Text #7

Max Range: 1.5987. Min Range: -1.5987

Max Act: 0.6343. Min Act: -0.0000

Data Index: 428106 (C4 (Web Text))

Max Activating Token Index: 179

Text #8

Max Range: 1.5987. Min Range: -1.5987

Max Act: 0.6342. Min Act: -0.0000

Data Index: 848837 (C4 (Web Text))

Max Activating Token Index: 448

Text #9

Max Range: 1.5987. Min Range: -1.5987

Max Act: 0.6244. Min Act: -0.0000

Data Index: 1159402 (C4 (Web Text))

Max Activating Token Index: 694

Text #10

Max Range: 1.5987. Min Range: -1.5987

Max Act: 0.6166. Min Act: -0.0000

Data Index: 400049 (C4 (Web Text))

Max Activating Token Index: 103

Text #11

Max Range: 1.5987. Min Range: -1.5987

Max Act: 0.6166. Min Act: -0.0000

Data Index: 297917 (C4 (Web Text))

Max Activating Token Index: 503

Text #12

Max Range: 1.5987. Min Range: -1.5987

Max Act: 0.6111. Min Act: -0.0000

Data Index: 567561 (C4 (Web Text))

Max Activating Token Index: 476

Text #13

Max Range: 1.5987. Min Range: -1.5987

Max Act: 0.6014. Min Act: -0.0000

Data Index: 1240233 (C4 (Web Text))

Max Activating Token Index: 420

Text #14

Max Range: 1.5987. Min Range: -1.5987

Max Act: 0.5989. Min Act: -0.0000

Data Index: 944439 (C4 (Web Text))

Max Activating Token Index: 394

Text #15

Max Range: 1.5987. Min Range: -1.5987

Max Act: 0.5968. Min Act: -0.0000

Data Index: 880985 (C4 (Web Text))

Max Activating Token Index: 111

Text #16

Max Range: 1.5987. Min Range: -1.5987

Max Act: 0.5568. Min Act: -0.0000

Data Index: 771507 (C4 (Web Text))

Max Activating Token Index: 862

Text #17

Max Range: 1.5987. Min Range: -1.5987

Max Act: 0.5562. Min Act: -0.0000

Data Index: 1134273 (C4 (Web Text))

Max Activating Token Index: 537

Text #18

Max Range: 1.5987. Min Range: -1.5987

Max Act: 0.5940. Min Act: -0.0000

Data Index: 564081 (C4 (Web Text))

Max Activating Token Index: 14

Text #19

Max Range: 1.5987. Min Range: -1.5987

Max Act: 0.5457. Min Act: -0.0000

Data Index: 1047721 (C4 (Web Text))

Max Activating Token Index: 358