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

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

Neuron 1890 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: 0.4549. Min Range: -0.4549

Max Act: 0.4549. Min Act: -0.0001

Data Index: 1453703 (Python Code)

Max Activating Token Index: 893

Text #1

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.4371. Min Act: -0.0001

Data Index: 1513522 (Python Code)

Max Activating Token Index: 8

Text #2

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.4423. Min Act: -0.0001

Data Index: 1521914 (Python Code)

Max Activating Token Index: 735

Text #3

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.4126. Min Act: -0.0001

Data Index: 1527104 (Python Code)

Max Activating Token Index: 526

Text #4

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.4294. Min Act: -0.0001

Data Index: 1366052 (Python Code)

Max Activating Token Index: 822

Text #5

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.4441. Min Act: -0.0001

Data Index: 1587813 (Python Code)

Max Activating Token Index: 814

Text #6

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.4172. Min Act: -0.0001

Data Index: 1489971 (Python Code)

Max Activating Token Index: 39

Text #7

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.4052. Min Act: -0.0001

Data Index: 1381035 (Python Code)

Max Activating Token Index: 862

Text #8

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.4076. Min Act: -0.0001

Data Index: 1464350 (Python Code)

Max Activating Token Index: 189

Text #9

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.4290. Min Act: -0.0001

Data Index: 1529717 (Python Code)

Max Activating Token Index: 968

Text #10

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.3994. Min Act: -0.0001

Data Index: 1586148 (Python Code)

Max Activating Token Index: 9

Text #11

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.4057. Min Act: -0.0001

Data Index: 1364622 (Python Code)

Max Activating Token Index: 925

Text #12

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.3959. Min Act: -0.0001

Data Index: 1420312 (Python Code)

Max Activating Token Index: 683

Text #13

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.4050. Min Act: -0.0001

Data Index: 1517944 (Python Code)

Max Activating Token Index: 124

Text #14

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.3881. Min Act: -0.0001

Data Index: 1507717 (Python Code)

Max Activating Token Index: 873

Text #15

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.3772. Min Act: -0.0001

Data Index: 1635875 (Python Code)

Max Activating Token Index: 782

Text #16

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.4070. Min Act: -0.0001

Data Index: 1461329 (Python Code)

Max Activating Token Index: 842

Text #17

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.4149. Min Act: -0.0001

Data Index: 1622624 (Python Code)

Max Activating Token Index: 766

Text #18

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.3770. Min Act: -0.0001

Data Index: 1570462 (Python Code)

Max Activating Token Index: 531

Text #19

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.3975. Min Act: -0.0001

Data Index: 1600544 (Python Code)

Max Activating Token Index: 761