Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 148 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.6818. Min Act: -0.0001

Data Index: 1620429 (Python Code)

Max Activating Token Index: 671

Text #1

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.6534. Min Act: -0.0001

Data Index: 1476590 (Python Code)

Max Activating Token Index: 864

Text #2

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.6523. Min Act: -0.0001

Data Index: 1465843 (Python Code)

Max Activating Token Index: 903

Text #3

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.6427. Min Act: -0.0001

Data Index: 1581522 (Python Code)

Max Activating Token Index: 722

Text #4

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.6325. Min Act: -0.0001

Data Index: 1503699 (Python Code)

Max Activating Token Index: 849

Text #5

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.6085. Min Act: -0.0001

Data Index: 1493265 (Python Code)

Max Activating Token Index: 754

Text #6

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.6468. Min Act: -0.0001

Data Index: 1634456 (Python Code)

Max Activating Token Index: 919

Text #7

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.6077. Min Act: -0.0001

Data Index: 1523494 (Python Code)

Max Activating Token Index: 358

Text #8

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.5964. Min Act: -0.0001

Data Index: 1467898 (Python Code)

Max Activating Token Index: 720

Text #9

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.5914. Min Act: -0.0001

Data Index: 1644452 (Python Code)

Max Activating Token Index: 964

Text #10

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.6083. Min Act: -0.0001

Data Index: 1390823 (Python Code)

Max Activating Token Index: 566

Text #11

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.5858. Min Act: -0.0001

Data Index: 1545202 (Python Code)

Max Activating Token Index: 994

Text #12

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.5839. Min Act: -0.0001

Data Index: 1548403 (Python Code)

Max Activating Token Index: 360

Text #13

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.5832. Min Act: -0.0001

Data Index: 1391380 (Python Code)

Max Activating Token Index: 849

Text #14

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.5955. Min Act: -0.0001

Data Index: 1383567 (Python Code)

Max Activating Token Index: 770

Text #15

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.5926. Min Act: -0.0001

Data Index: 1520123 (Python Code)

Max Activating Token Index: 102

Text #16

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.5698. Min Act: -0.0001

Data Index: 1619040 (Python Code)

Max Activating Token Index: 643

Text #17

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.5831. Min Act: -0.0001

Data Index: 1412183 (Python Code)

Max Activating Token Index: 988

Text #18

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.5828. Min Act: -0.0001

Data Index: 1550479 (Python Code)

Max Activating Token Index: 664

Text #19

Max Range: 0.6818. Min Range: -0.6818

Max Act: 0.5850. Min Act: -0.0001

Data Index: 1369358 (Python Code)

Max Activating Token Index: 754