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

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

Neuron 1920 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0110. Min Range: -1.0110

Max Act: 1.0110. Min Act: -0.0000

Data Index: 761748 (C4 (Web Text))

Max Activating Token Index: 940

Text #1

Max Range: 1.0110. Min Range: -1.0110

Max Act: 0.8761. Min Act: -0.0000

Data Index: 1464852 (Python Code)

Max Activating Token Index: 744

Text #2

Max Range: 1.0110. Min Range: -1.0110

Max Act: 0.8961. Min Act: -0.0000

Data Index: 570800 (C4 (Web Text))

Max Activating Token Index: 405

Text #3

Max Range: 1.0110. Min Range: -1.0110

Max Act: 0.8066. Min Act: -0.0000

Data Index: 1632428 (Python Code)

Max Activating Token Index: 894

Text #4

Max Range: 1.0110. Min Range: -1.0110

Max Act: 0.8278. Min Act: -0.0000

Data Index: 1552609 (Python Code)

Max Activating Token Index: 876

Text #5

Max Range: 1.0110. Min Range: -1.0110

Max Act: 0.7958. Min Act: -0.0000

Data Index: 233317 (C4 (Web Text))

Max Activating Token Index: 481

Text #6

Max Range: 1.0110. Min Range: -1.0110

Max Act: 0.7160. Min Act: -0.0000

Data Index: 1642073 (Python Code)

Max Activating Token Index: 403

Text #7

Max Range: 1.0110. Min Range: -1.0110

Max Act: 0.7990. Min Act: -0.0000

Data Index: 1615369 (Python Code)

Max Activating Token Index: 251

Text #8

Max Range: 1.0110. Min Range: -1.0110

Max Act: 0.8315. Min Act: -0.0000

Data Index: 1402986 (Python Code)

Max Activating Token Index: 398

Text #9

Max Range: 1.0110. Min Range: -1.0110

Max Act: 0.7158. Min Act: -0.0000

Data Index: 1556461 (Python Code)

Max Activating Token Index: 816

Text #10

Max Range: 1.0110. Min Range: -1.0110

Max Act: 0.7353. Min Act: -0.0000

Data Index: 1611543 (Python Code)

Max Activating Token Index: 698

Text #11

Max Range: 1.0110. Min Range: -1.0110

Max Act: 0.8197. Min Act: -0.0000

Data Index: 1565436 (Python Code)

Max Activating Token Index: 432

Text #12

Max Range: 1.0110. Min Range: -1.0110

Max Act: 0.7316. Min Act: -0.0000

Data Index: 1439242 (Python Code)

Max Activating Token Index: 567

Text #13

Max Range: 1.0110. Min Range: -1.0110

Max Act: 0.6979. Min Act: -0.0000

Data Index: 548576 (C4 (Web Text))

Max Activating Token Index: 791

Text #14

Max Range: 1.0110. Min Range: -1.0110

Max Act: 0.6907. Min Act: -0.0000

Data Index: 1076874 (C4 (Web Text))

Max Activating Token Index: 141

Text #15

Max Range: 1.0110. Min Range: -1.0110

Max Act: 0.6441. Min Act: -0.0000

Data Index: 276907 (C4 (Web Text))

Max Activating Token Index: 847

Text #16

Max Range: 1.0110. Min Range: -1.0110

Max Act: 0.7000. Min Act: -0.0000

Data Index: 1559995 (Python Code)

Max Activating Token Index: 806

Text #17

Max Range: 1.0110. Min Range: -1.0110

Max Act: 0.6302. Min Act: -0.0000

Data Index: 1340477 (C4 (Web Text))

Max Activating Token Index: 338

Text #18

Max Range: 1.0110. Min Range: -1.0110

Max Act: 0.6504. Min Act: -0.0000

Data Index: 1401272 (Python Code)

Max Activating Token Index: 222

Text #19

Max Range: 1.0110. Min Range: -1.0110

Max Act: 0.6403. Min Act: -0.0000

Data Index: 1541085 (Python Code)

Max Activating Token Index: 955