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

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

Neuron 1118 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9783. Min Range: -0.9783

Max Act: 0.9783. Min Act: -0.0001

Data Index: 1416449 (Python Code)

Max Activating Token Index: 597

Text #1

Max Range: 0.9783. Min Range: -0.9783

Max Act: 0.9663. Min Act: -0.0000

Data Index: 1591795 (Python Code)

Max Activating Token Index: 135

Text #2

Max Range: 0.9783. Min Range: -0.9783

Max Act: 0.8719. Min Act: -0.0000

Data Index: 1460552 (Python Code)

Max Activating Token Index: 647

Text #3

Max Range: 0.9783. Min Range: -0.9783

Max Act: 0.9089. Min Act: -0.0000

Data Index: 1360916 (Python Code)

Max Activating Token Index: 592

Text #4

Max Range: 0.9783. Min Range: -0.9783

Max Act: 0.8633. Min Act: -0.0001

Data Index: 1498762 (Python Code)

Max Activating Token Index: 789

Text #5

Max Range: 0.9783. Min Range: -0.9783

Max Act: 0.7763. Min Act: -0.0001

Data Index: 1565840 (Python Code)

Max Activating Token Index: 609

Text #6

Max Range: 0.9783. Min Range: -0.9783

Max Act: 0.6952. Min Act: -0.0001

Data Index: 1541190 (Python Code)

Max Activating Token Index: 361

Text #7

Max Range: 0.9783. Min Range: -0.9783

Max Act: 0.7154. Min Act: -0.0000

Data Index: 1552420 (Python Code)

Max Activating Token Index: 247

Text #8

Max Range: 0.9783. Min Range: -0.9783

Max Act: 0.6996. Min Act: -0.0000

Data Index: 1442384 (Python Code)

Max Activating Token Index: 1003

Text #9

Max Range: 0.9783. Min Range: -0.9783

Max Act: 0.6187. Min Act: -0.0000

Data Index: 1589528 (Python Code)

Max Activating Token Index: 62

Text #10

Max Range: 0.9783. Min Range: -0.9783

Max Act: 0.6279. Min Act: -0.0000

Data Index: 1391598 (Python Code)

Max Activating Token Index: 727

Text #11

Max Range: 0.9783. Min Range: -0.9783

Max Act: 0.6464. Min Act: -0.0000

Data Index: 1532308 (Python Code)

Max Activating Token Index: 973

Text #12

Max Range: 0.9783. Min Range: -0.9783

Max Act: 0.6464. Min Act: -0.0001

Data Index: 1581692 (Python Code)

Max Activating Token Index: 389

Text #13

Max Range: 0.9783. Min Range: -0.9783

Max Act: 0.6063. Min Act: -0.0000

Data Index: 1420672 (Python Code)

Max Activating Token Index: 943

Text #14

Max Range: 0.9783. Min Range: -0.9783

Max Act: 0.6156. Min Act: -0.0000

Data Index: 1502431 (Python Code)

Max Activating Token Index: 931

Text #15

Max Range: 0.9783. Min Range: -0.9783

Max Act: 0.6380. Min Act: -0.0000

Data Index: 1445180 (Python Code)

Max Activating Token Index: 827

Text #16

Max Range: 0.9783. Min Range: -0.9783

Max Act: 0.5943. Min Act: -0.0000

Data Index: 1573463 (Python Code)

Max Activating Token Index: 840

Text #17

Max Range: 0.9783. Min Range: -0.9783

Max Act: 0.6273. Min Act: -0.0000

Data Index: 1587172 (Python Code)

Max Activating Token Index: 717

Text #18

Max Range: 0.9783. Min Range: -0.9783

Max Act: 0.6078. Min Act: -0.0000

Data Index: 1540405 (Python Code)

Max Activating Token Index: 424

Text #19

Max Range: 0.9783. Min Range: -0.9783

Max Act: 0.6059. Min Act: -0.0000

Data Index: 1597468 (Python Code)

Max Activating Token Index: 857