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

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

Neuron 3620 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: 2.0169. Min Range: -2.0169

Max Act: 2.0123. Min Act: -0.0000

Data Index: 1454403 (Python Code)

Max Activating Token Index: 999

Text #1

Max Range: 2.0169. Min Range: -2.0169

Max Act: 1.8878. Min Act: -0.0000

Data Index: 1493782 (Python Code)

Max Activating Token Index: 234

Text #2

Max Range: 2.0169. Min Range: -2.0169

Max Act: 1.9582. Min Act: -0.0000

Data Index: 1636541 (Python Code)

Max Activating Token Index: 525

Text #3

Max Range: 2.0169. Min Range: -2.0169

Max Act: 2.0169. Min Act: -0.0000

Data Index: 1624739 (Python Code)

Max Activating Token Index: 87

Text #4

Max Range: 2.0169. Min Range: -2.0169

Max Act: 1.7753. Min Act: -0.0000

Data Index: 1544152 (Python Code)

Max Activating Token Index: 307

Text #5

Max Range: 2.0169. Min Range: -2.0169

Max Act: 1.7218. Min Act: -0.0000

Data Index: 1574017 (Python Code)

Max Activating Token Index: 64

Text #6

Max Range: 2.0169. Min Range: -2.0169

Max Act: 1.6262. Min Act: -0.0000

Data Index: 1542127 (Python Code)

Max Activating Token Index: 471

Text #7

Max Range: 2.0169. Min Range: -2.0169

Max Act: 1.6832. Min Act: -0.0000

Data Index: 1416936 (Python Code)

Max Activating Token Index: 55

Text #8

Max Range: 2.0169. Min Range: -2.0169

Max Act: 1.6972. Min Act: -0.0000

Data Index: 1575835 (Python Code)

Max Activating Token Index: 728

Text #9

Max Range: 2.0169. Min Range: -2.0169

Max Act: 1.7031. Min Act: -0.0000

Data Index: 1636604 (Python Code)

Max Activating Token Index: 337

Text #10

Max Range: 2.0169. Min Range: -2.0169

Max Act: 1.6482. Min Act: -0.0000

Data Index: 1598609 (Python Code)

Max Activating Token Index: 508

Text #11

Max Range: 2.0169. Min Range: -2.0169

Max Act: 1.7333. Min Act: -0.0000

Data Index: 1614142 (Python Code)

Max Activating Token Index: 1006

Text #12

Max Range: 2.0169. Min Range: -2.0169

Max Act: 1.6343. Min Act: -0.0000

Data Index: 1364067 (Python Code)

Max Activating Token Index: 339

Text #13

Max Range: 2.0169. Min Range: -2.0169

Max Act: 1.5490. Min Act: -0.0000

Data Index: 1410540 (Python Code)

Max Activating Token Index: 981

Text #14

Max Range: 2.0169. Min Range: -2.0169

Max Act: 1.6222. Min Act: -0.0000

Data Index: 1482995 (Python Code)

Max Activating Token Index: 397

Text #15

Max Range: 2.0169. Min Range: -2.0169

Max Act: 1.6233. Min Act: -0.0000

Data Index: 1656453 (Python Code)

Max Activating Token Index: 54

Text #16

Max Range: 2.0169. Min Range: -2.0169

Max Act: 1.6819. Min Act: -0.0000

Data Index: 1542060 (Python Code)

Max Activating Token Index: 901

Text #17

Max Range: 2.0169. Min Range: -2.0169

Max Act: 1.6773. Min Act: -0.0000

Data Index: 1621241 (Python Code)

Max Activating Token Index: 565

Text #18

Max Range: 2.0169. Min Range: -2.0169

Max Act: 1.5738. Min Act: -0.0000

Data Index: 1558398 (Python Code)

Max Activating Token Index: 67

Text #19

Max Range: 2.0169. Min Range: -2.0169

Max Act: 1.6652. Min Act: -0.0000

Data Index: 1624386 (Python Code)

Max Activating Token Index: 345