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

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

Neuron 975 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3916. Min Range: -1.3916

Max Act: 1.3916. Min Act: -0.0001

Data Index: 1485513 (Python Code)

Max Activating Token Index: 18

Text #1

Max Range: 1.3916. Min Range: -1.3916

Max Act: 1.2300. Min Act: -0.0001

Data Index: 1610002 (Python Code)

Max Activating Token Index: 237

Text #2

Max Range: 1.3916. Min Range: -1.3916

Max Act: 1.1089. Min Act: -0.0001

Data Index: 1598422 (Python Code)

Max Activating Token Index: 831

Text #3

Max Range: 1.3916. Min Range: -1.3916

Max Act: 1.1297. Min Act: -0.0001

Data Index: 1427473 (Python Code)

Max Activating Token Index: 6

Text #4

Max Range: 1.3916. Min Range: -1.3916

Max Act: 1.0599. Min Act: -0.0001

Data Index: 1419181 (Python Code)

Max Activating Token Index: 35

Text #5

Max Range: 1.3916. Min Range: -1.3916

Max Act: 0.9326. Min Act: -0.0001

Data Index: 1442983 (Python Code)

Max Activating Token Index: 290

Text #6

Max Range: 1.3916. Min Range: -1.3916

Max Act: 1.0921. Min Act: -0.0001

Data Index: 1414385 (Python Code)

Max Activating Token Index: 597

Text #7

Max Range: 1.3916. Min Range: -1.3916

Max Act: 1.0350. Min Act: -0.0000

Data Index: 1609298 (Python Code)

Max Activating Token Index: 159

Text #8

Max Range: 1.3916. Min Range: -1.3916

Max Act: 1.0056. Min Act: -0.0001

Data Index: 1410732 (Python Code)

Max Activating Token Index: 688

Text #9

Max Range: 1.3916. Min Range: -1.3916

Max Act: 1.0692. Min Act: -0.0001

Data Index: 1414158 (Python Code)

Max Activating Token Index: 180

Text #10

Max Range: 1.3916. Min Range: -1.3916

Max Act: 1.0083. Min Act: -0.0000

Data Index: 1468994 (Python Code)

Max Activating Token Index: 53

Text #11

Max Range: 1.3916. Min Range: -1.3916

Max Act: 0.9955. Min Act: -0.0001

Data Index: 1371632 (Python Code)

Max Activating Token Index: 39

Text #12

Max Range: 1.3916. Min Range: -1.3916

Max Act: 0.9958. Min Act: -0.0001

Data Index: 1646610 (Python Code)

Max Activating Token Index: 394

Text #13

Max Range: 1.3916. Min Range: -1.3916

Max Act: 1.0873. Min Act: -0.0000

Data Index: 1501406 (Python Code)

Max Activating Token Index: 478

Text #14

Max Range: 1.3916. Min Range: -1.3916

Max Act: 0.9788. Min Act: -0.0000

Data Index: 1423062 (Python Code)

Max Activating Token Index: 6

Text #15

Max Range: 1.3916. Min Range: -1.3916

Max Act: 0.8456. Min Act: -0.0001

Data Index: 1409283 (Python Code)

Max Activating Token Index: 982

Text #16

Max Range: 1.3916. Min Range: -1.3916

Max Act: 0.9431. Min Act: -0.0001

Data Index: 1419394 (Python Code)

Max Activating Token Index: 339

Text #17

Max Range: 1.3916. Min Range: -1.3916

Max Act: 0.9833. Min Act: -0.0000

Data Index: 1390994 (Python Code)

Max Activating Token Index: 19

Text #18

Max Range: 1.3916. Min Range: -1.3916

Max Act: 0.9911. Min Act: -0.0000

Data Index: 1551149 (Python Code)

Max Activating Token Index: 225

Text #19

Max Range: 1.3916. Min Range: -1.3916

Max Act: 0.9834. Min Act: -0.0000

Data Index: 1580194 (Python Code)

Max Activating Token Index: 312