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

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

Neuron 34 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: 1.0409. Min Range: -1.0409

Max Act: 1.0409. Min Act: -0.0000

Data Index: 1575931 (Python Code)

Max Activating Token Index: 596

Text #1

Max Range: 1.0409. Min Range: -1.0409

Max Act: 0.9564. Min Act: -0.0000

Data Index: 1606746 (Python Code)

Max Activating Token Index: 523

Text #2

Max Range: 1.0409. Min Range: -1.0409

Max Act: 0.8827. Min Act: -0.0000

Data Index: 973314 (C4 (Web Text))

Max Activating Token Index: 658

Text #3

Max Range: 1.0409. Min Range: -1.0409

Max Act: 0.8079. Min Act: -0.0000

Data Index: 1458800 (Python Code)

Max Activating Token Index: 503

Text #4

Max Range: 1.0409. Min Range: -1.0409

Max Act: 0.8585. Min Act: -0.0000

Data Index: 1379890 (Python Code)

Max Activating Token Index: 848

Text #5

Max Range: 1.0409. Min Range: -1.0409

Max Act: 0.8154. Min Act: -0.0000

Data Index: 154977 (C4 (Web Text))

Max Activating Token Index: 462

Text #6

Max Range: 1.0409. Min Range: -1.0409

Max Act: 0.8146. Min Act: -0.0000

Data Index: 1380690 (Python Code)

Max Activating Token Index: 393

Text #7

Max Range: 1.0409. Min Range: -1.0409

Max Act: 0.9270. Min Act: -0.0000

Data Index: 1420558 (Python Code)

Max Activating Token Index: 739

Text #8

Max Range: 1.0409. Min Range: -1.0409

Max Act: 0.8114. Min Act: -0.0000

Data Index: 1518459 (Python Code)

Max Activating Token Index: 82

Text #9

Max Range: 1.0409. Min Range: -1.0409

Max Act: 0.7616. Min Act: -0.0000

Data Index: 336717 (C4 (Web Text))

Max Activating Token Index: 139

Text #10

Max Range: 1.0409. Min Range: -1.0409

Max Act: 0.7196. Min Act: -0.0000

Data Index: 1379697 (Python Code)

Max Activating Token Index: 223

Text #11

Max Range: 1.0409. Min Range: -1.0409

Max Act: 0.7190. Min Act: -0.0000

Data Index: 148864 (C4 (Web Text))

Max Activating Token Index: 302

Text #12

Max Range: 1.0409. Min Range: -1.0409

Max Act: 0.6443. Min Act: -0.0000

Data Index: 434551 (C4 (Web Text))

Max Activating Token Index: 143

Text #13

Max Range: 1.0409. Min Range: -1.0409

Max Act: 0.6992. Min Act: -0.0000

Data Index: 1412225 (Python Code)

Max Activating Token Index: 74

Text #14

Max Range: 1.0409. Min Range: -1.0409

Max Act: 0.6371. Min Act: -0.0000

Data Index: 1487641 (Python Code)

Max Activating Token Index: 178

Text #15

Max Range: 1.0409. Min Range: -1.0409

Max Act: 0.6337. Min Act: -0.0000

Data Index: 1585836 (Python Code)

Max Activating Token Index: 43

Text #16

Max Range: 1.0409. Min Range: -1.0409

Max Act: 0.5886. Min Act: -0.0000

Data Index: 1404153 (Python Code)

Max Activating Token Index: 280

Text #17

Max Range: 1.0409. Min Range: -1.0409

Max Act: 0.5698. Min Act: -0.0000

Data Index: 1489260 (Python Code)

Max Activating Token Index: 360

Text #18

Max Range: 1.0409. Min Range: -1.0409

Max Act: 0.5991. Min Act: -0.0000

Data Index: 1424734 (Python Code)

Max Activating Token Index: 183

Text #19

Max Range: 1.0409. Min Range: -1.0409

Max Act: 0.6550. Min Act: -0.0000

Data Index: 1544133 (Python Code)

Max Activating Token Index: 215