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

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

Neuron 300 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.3826. Min Range: -1.3826

Max Act: 1.3826. Min Act: -0.0002

Data Index: 1592348 (Python Code)

Max Activating Token Index: 41

Text #1

Max Range: 1.3826. Min Range: -1.3826

Max Act: 1.2038. Min Act: -0.0002

Data Index: 1415305 (Python Code)

Max Activating Token Index: 341

Text #2

Max Range: 1.3826. Min Range: -1.3826

Max Act: 1.1901. Min Act: -0.0002

Data Index: 1427409 (Python Code)

Max Activating Token Index: 204

Text #3

Max Range: 1.3826. Min Range: -1.3826

Max Act: 1.1933. Min Act: -0.0002

Data Index: 1462050 (Python Code)

Max Activating Token Index: 75

Text #4

Max Range: 1.3826. Min Range: -1.3826

Max Act: 1.1350. Min Act: -0.0002

Data Index: 1481956 (Python Code)

Max Activating Token Index: 22

Text #5

Max Range: 1.3826. Min Range: -1.3826

Max Act: 1.0995. Min Act: -0.0002

Data Index: 1468361 (Python Code)

Max Activating Token Index: 10

Text #6

Max Range: 1.3826. Min Range: -1.3826

Max Act: 1.1157. Min Act: -0.0002

Data Index: 1583373 (Python Code)

Max Activating Token Index: 7

Text #7

Max Range: 1.3826. Min Range: -1.3826

Max Act: 1.0829. Min Act: -0.0002

Data Index: 1611302 (Python Code)

Max Activating Token Index: 86

Text #8

Max Range: 1.3826. Min Range: -1.3826

Max Act: 1.0668. Min Act: -0.0002

Data Index: 533363 (C4 (Web Text))

Max Activating Token Index: 322

Text #9

Max Range: 1.3826. Min Range: -1.3826

Max Act: 1.0360. Min Act: -0.0002

Data Index: 1485378 (Python Code)

Max Activating Token Index: 691

Text #10

Max Range: 1.3826. Min Range: -1.3826

Max Act: 1.0412. Min Act: -0.0002

Data Index: 1422887 (Python Code)

Max Activating Token Index: 204

Text #11

Max Range: 1.3826. Min Range: -1.3826

Max Act: 1.0418. Min Act: -0.0002

Data Index: 799577 (C4 (Web Text))

Max Activating Token Index: 234

Text #12

Max Range: 1.3826. Min Range: -1.3826

Max Act: 1.0275. Min Act: -0.0002

Data Index: 1541084 (Python Code)

Max Activating Token Index: 43

Text #13

Max Range: 1.3826. Min Range: -1.3826

Max Act: 1.0078. Min Act: -0.0002

Data Index: 1396989 (Python Code)

Max Activating Token Index: 87

Text #14

Max Range: 1.3826. Min Range: -1.3826

Max Act: 1.0114. Min Act: -0.0002

Data Index: 1397439 (Python Code)

Max Activating Token Index: 158

Text #15

Max Range: 1.3826. Min Range: -1.3826

Max Act: 0.9975. Min Act: -0.0002

Data Index: 1451281 (Python Code)

Max Activating Token Index: 114

Text #16

Max Range: 1.3826. Min Range: -1.3826

Max Act: 0.9660. Min Act: -0.0002

Data Index: 1401125 (Python Code)

Max Activating Token Index: 22

Text #17

Max Range: 1.3826. Min Range: -1.3826

Max Act: 0.9615. Min Act: -0.0002

Data Index: 1516630 (Python Code)

Max Activating Token Index: 78

Text #18

Max Range: 1.3826. Min Range: -1.3826

Max Act: 0.9747. Min Act: -0.0002

Data Index: 1448641 (Python Code)

Max Activating Token Index: 197

Text #19

Max Range: 1.3826. Min Range: -1.3826

Max Act: 0.9692. Min Act: -0.0002

Data Index: 1505581 (Python Code)

Max Activating Token Index: 548