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

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

Neuron 1973 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7084. Min Range: -0.7084

Max Act: 0.7053. Min Act: -0.0001

Data Index: 1383887 (Python Code)

Max Activating Token Index: 484

Text #1

Max Range: 0.7084. Min Range: -0.7084

Max Act: 0.7072. Min Act: -0.0001

Data Index: 1485274 (Python Code)

Max Activating Token Index: 53

Text #2

Max Range: 0.7084. Min Range: -0.7084

Max Act: 0.7084. Min Act: -0.0001

Data Index: 1484938 (Python Code)

Max Activating Token Index: 60

Text #3

Max Range: 0.7084. Min Range: -0.7084

Max Act: 0.6605. Min Act: -0.0001

Data Index: 1585358 (Python Code)

Max Activating Token Index: 772

Text #4

Max Range: 0.7084. Min Range: -0.7084

Max Act: 0.6598. Min Act: -0.0001

Data Index: 1567366 (Python Code)

Max Activating Token Index: 447

Text #5

Max Range: 0.7084. Min Range: -0.7084

Max Act: 0.6614. Min Act: -0.0001

Data Index: 1543645 (Python Code)

Max Activating Token Index: 300

Text #6

Max Range: 0.7084. Min Range: -0.7084

Max Act: 0.6202. Min Act: -0.0001

Data Index: 1479204 (Python Code)

Max Activating Token Index: 907

Text #7

Max Range: 0.7084. Min Range: -0.7084

Max Act: 0.6165. Min Act: -0.0001

Data Index: 1616253 (Python Code)

Max Activating Token Index: 378

Text #8

Max Range: 0.7084. Min Range: -0.7084

Max Act: 0.6309. Min Act: -0.0001

Data Index: 1507675 (Python Code)

Max Activating Token Index: 146

Text #9

Max Range: 0.7084. Min Range: -0.7084

Max Act: 0.6327. Min Act: -0.0001

Data Index: 1448531 (Python Code)

Max Activating Token Index: 633

Text #10

Max Range: 0.7084. Min Range: -0.7084

Max Act: 0.6509. Min Act: -0.0001

Data Index: 1451723 (Python Code)

Max Activating Token Index: 373

Text #11

Max Range: 0.7084. Min Range: -0.7084

Max Act: 0.6128. Min Act: -0.0001

Data Index: 1600797 (Python Code)

Max Activating Token Index: 660

Text #12

Max Range: 0.7084. Min Range: -0.7084

Max Act: 0.6310. Min Act: -0.0001

Data Index: 1560709 (Python Code)

Max Activating Token Index: 161

Text #13

Max Range: 0.7084. Min Range: -0.7084

Max Act: 0.6105. Min Act: -0.0001

Data Index: 1416872 (Python Code)

Max Activating Token Index: 553

Text #14

Max Range: 0.7084. Min Range: -0.7084

Max Act: 0.6060. Min Act: -0.0001

Data Index: 1509515 (Python Code)

Max Activating Token Index: 111

Text #15

Max Range: 0.7084. Min Range: -0.7084

Max Act: 0.6049. Min Act: -0.0001

Data Index: 1539274 (Python Code)

Max Activating Token Index: 15

Text #16

Max Range: 0.7084. Min Range: -0.7084

Max Act: 0.5845. Min Act: -0.0001

Data Index: 1636496 (Python Code)

Max Activating Token Index: 59

Text #17

Max Range: 0.7084. Min Range: -0.7084

Max Act: 0.5791. Min Act: -0.0001

Data Index: 1604869 (Python Code)

Max Activating Token Index: 847

Text #18

Max Range: 0.7084. Min Range: -0.7084

Max Act: 0.6006. Min Act: -0.0001

Data Index: 1511387 (Python Code)

Max Activating Token Index: 88

Text #19

Max Range: 0.7084. Min Range: -0.7084

Max Act: 0.5803. Min Act: -0.0001

Data Index: 1637042 (Python Code)

Max Activating Token Index: 749