Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 701 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.1146. Min Act: -0.0003

Data Index: 1636920 (Python Code)

Max Activating Token Index: 798

Text #1

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.1104. Min Act: -0.0003

Data Index: 1386881 (Python Code)

Max Activating Token Index: 800

Text #2

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.1108. Min Act: -0.0003

Data Index: 1626261 (Python Code)

Max Activating Token Index: 836

Text #3

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.1067. Min Act: -0.0003

Data Index: 1514471 (Python Code)

Max Activating Token Index: 540

Text #4

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.1041. Min Act: -0.0003

Data Index: 1540024 (Python Code)

Max Activating Token Index: 671

Text #5

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.1032. Min Act: -0.0003

Data Index: 1477797 (Python Code)

Max Activating Token Index: 866

Text #6

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0992. Min Act: -0.0003

Data Index: 1567244 (Python Code)

Max Activating Token Index: 617

Text #7

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0959. Min Act: -0.0003

Data Index: 1572819 (Python Code)

Max Activating Token Index: 789

Text #8

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0975. Min Act: -0.0003

Data Index: 1636901 (Python Code)

Max Activating Token Index: 619

Text #9

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0970. Min Act: -0.0003

Data Index: 1434920 (Python Code)

Max Activating Token Index: 808

Text #10

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0985. Min Act: -0.0003

Data Index: 1424021 (Python Code)

Max Activating Token Index: 331

Text #11

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0968. Min Act: -0.0003

Data Index: 1440218 (Python Code)

Max Activating Token Index: 587

Text #12

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0960. Min Act: -0.0003

Data Index: 1572784 (Python Code)

Max Activating Token Index: 798

Text #13

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0973. Min Act: -0.0003

Data Index: 1534854 (Python Code)

Max Activating Token Index: 938

Text #14

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0944. Min Act: -0.0003

Data Index: 1449984 (Python Code)

Max Activating Token Index: 790

Text #15

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0953. Min Act: -0.0003

Data Index: 1588168 (Python Code)

Max Activating Token Index: 639

Text #16

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0930. Min Act: -0.0003

Data Index: 1579825 (Python Code)

Max Activating Token Index: 766

Text #17

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0924. Min Act: -0.0003

Data Index: 1593821 (Python Code)

Max Activating Token Index: 652

Text #18

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0941. Min Act: -0.0003

Data Index: 1449621 (Python Code)

Max Activating Token Index: 565

Text #19

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0952. Min Act: -0.0003

Data Index: 1558571 (Python Code)

Max Activating Token Index: 677