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

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

Neuron 1627 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6075. Min Range: -0.6075

Max Act: 0.5774. Min Act: -0.0000

Data Index: 91791 (C4 (Web Text))

Max Activating Token Index: 159

Text #1

Max Range: 0.6075. Min Range: -0.6075

Max Act: 0.5748. Min Act: -0.0000

Data Index: 1422840 (Python Code)

Max Activating Token Index: 23

Text #2

Max Range: 0.6075. Min Range: -0.6075

Max Act: 0.6075. Min Act: -0.0000

Data Index: 781060 (C4 (Web Text))

Max Activating Token Index: 732

Text #3

Max Range: 0.6075. Min Range: -0.6075

Max Act: 0.5511. Min Act: -0.0000

Data Index: 338665 (C4 (Web Text))

Max Activating Token Index: 999

Text #4

Max Range: 0.6075. Min Range: -0.6075

Max Act: 0.5431. Min Act: -0.0000

Data Index: 665225 (C4 (Web Text))

Max Activating Token Index: 790

Text #5

Max Range: 0.6075. Min Range: -0.6075

Max Act: 0.4731. Min Act: -0.0000

Data Index: 1339616 (C4 (Web Text))

Max Activating Token Index: 613

Text #6

Max Range: 0.6075. Min Range: -0.6075

Max Act: 0.4615. Min Act: -0.0000

Data Index: 1157939 (C4 (Web Text))

Max Activating Token Index: 971

Text #7

Max Range: 0.6075. Min Range: -0.6075

Max Act: 0.5279. Min Act: -0.0000

Data Index: 1122578 (C4 (Web Text))

Max Activating Token Index: 351

Text #8

Max Range: 0.6075. Min Range: -0.6075

Max Act: 0.4748. Min Act: -0.0000

Data Index: 475256 (C4 (Web Text))

Max Activating Token Index: 595

Text #9

Max Range: 0.6075. Min Range: -0.6075

Max Act: 0.4254. Min Act: -0.0000

Data Index: 1213539 (C4 (Web Text))

Max Activating Token Index: 977

Text #10

Max Range: 0.6075. Min Range: -0.6075

Max Act: 0.4411. Min Act: -0.0000

Data Index: 1481268 (Python Code)

Max Activating Token Index: 48

Text #11

Max Range: 0.6075. Min Range: -0.6075

Max Act: 0.4212. Min Act: -0.0000

Data Index: 1392237 (Python Code)

Max Activating Token Index: 57

Text #12

Max Range: 0.6075. Min Range: -0.6075

Max Act: 0.4444. Min Act: -0.0000

Data Index: 337819 (C4 (Web Text))

Max Activating Token Index: 201

Text #13

Max Range: 0.6075. Min Range: -0.6075

Max Act: 0.4091. Min Act: -0.0000

Data Index: 949699 (C4 (Web Text))

Max Activating Token Index: 554

Text #14

Max Range: 0.6075. Min Range: -0.6075

Max Act: 0.4699. Min Act: -0.0000

Data Index: 1190838 (C4 (Web Text))

Max Activating Token Index: 798

Text #15

Max Range: 0.6075. Min Range: -0.6075

Max Act: 0.4243. Min Act: -0.0000

Data Index: 1285232 (C4 (Web Text))

Max Activating Token Index: 483

Text #16

Max Range: 0.6075. Min Range: -0.6075

Max Act: 0.4192. Min Act: -0.0000

Data Index: 1058940 (C4 (Web Text))

Max Activating Token Index: 991

Text #17

Max Range: 0.6075. Min Range: -0.6075

Max Act: 0.4313. Min Act: -0.0000

Data Index: 954974 (C4 (Web Text))

Max Activating Token Index: 950

Text #18

Max Range: 0.6075. Min Range: -0.6075

Max Act: 0.3886. Min Act: -0.0000

Data Index: 152521 (C4 (Web Text))

Max Activating Token Index: 563

Text #19

Max Range: 0.6075. Min Range: -0.6075

Max Act: 0.3979. Min Act: -0.0000

Data Index: 1424812 (Python Code)

Max Activating Token Index: 863