Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4416 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9121. Min Range: -0.9121

Max Act: 0.9121. Min Act: -0.0001

Data Index: 1496248 (Python Code)

Max Activating Token Index: 61

Text #1

Max Range: 0.9121. Min Range: -0.9121

Max Act: 0.8722. Min Act: -0.0001

Data Index: 1453615 (Python Code)

Max Activating Token Index: 917

Text #2

Max Range: 0.9121. Min Range: -0.9121

Max Act: 0.7940. Min Act: -0.0001

Data Index: 1566038 (Python Code)

Max Activating Token Index: 189

Text #3

Max Range: 0.9121. Min Range: -0.9121

Max Act: 0.8119. Min Act: -0.0001

Data Index: 1503371 (Python Code)

Max Activating Token Index: 736

Text #4

Max Range: 0.9121. Min Range: -0.9121

Max Act: 0.8361. Min Act: -0.0001

Data Index: 1521218 (Python Code)

Max Activating Token Index: 75

Text #5

Max Range: 0.9121. Min Range: -0.9121

Max Act: 0.7901. Min Act: -0.0001

Data Index: 1516360 (Python Code)

Max Activating Token Index: 153

Text #6

Max Range: 0.9121. Min Range: -0.9121

Max Act: 0.8575. Min Act: -0.0001

Data Index: 1372356 (Python Code)

Max Activating Token Index: 587

Text #7

Max Range: 0.9121. Min Range: -0.9121

Max Act: 0.8026. Min Act: -0.0001

Data Index: 1475598 (Python Code)

Max Activating Token Index: 78

Text #8

Max Range: 0.9121. Min Range: -0.9121

Max Act: 0.7881. Min Act: -0.0001

Data Index: 1444233 (Python Code)

Max Activating Token Index: 459

Text #9

Max Range: 0.9121. Min Range: -0.9121

Max Act: 0.8083. Min Act: -0.0001

Data Index: 1612035 (Python Code)

Max Activating Token Index: 723

Text #10

Max Range: 0.9121. Min Range: -0.9121

Max Act: 0.8003. Min Act: -0.0001

Data Index: 1511720 (Python Code)

Max Activating Token Index: 667

Text #11

Max Range: 0.9121. Min Range: -0.9121

Max Act: 0.7690. Min Act: -0.0001

Data Index: 1411366 (Python Code)

Max Activating Token Index: 214

Text #12

Max Range: 0.9121. Min Range: -0.9121

Max Act: 0.8051. Min Act: -0.0001

Data Index: 1464526 (Python Code)

Max Activating Token Index: 24

Text #13

Max Range: 0.9121. Min Range: -0.9121

Max Act: 0.7400. Min Act: -0.0001

Data Index: 1650738 (Python Code)

Max Activating Token Index: 750

Text #14

Max Range: 0.9121. Min Range: -0.9121

Max Act: 0.6354. Min Act: -0.0001

Data Index: 1384886 (Python Code)

Max Activating Token Index: 551

Text #15

Max Range: 0.9121. Min Range: -0.9121

Max Act: 0.7327. Min Act: -0.0001

Data Index: 1411367 (Python Code)

Max Activating Token Index: 137

Text #16

Max Range: 0.9121. Min Range: -0.9121

Max Act: 0.8388. Min Act: -0.0001

Data Index: 1474998 (Python Code)

Max Activating Token Index: 101

Text #17

Max Range: 0.9121. Min Range: -0.9121

Max Act: 0.8060. Min Act: -0.0001

Data Index: 1633730 (Python Code)

Max Activating Token Index: 39

Text #18

Max Range: 0.9121. Min Range: -0.9121

Max Act: 0.7596. Min Act: -0.0001

Data Index: 1596540 (Python Code)

Max Activating Token Index: 972

Text #19

Max Range: 0.9121. Min Range: -0.9121

Max Act: 0.7626. Min Act: -0.0001

Data Index: 1523671 (Python Code)

Max Activating Token Index: 537