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

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

Neuron 3792 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.1056. Min Act: -0.0001

Data Index: 1650948 (Python Code)

Max Activating Token Index: 145

Text #1

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.1063. Min Act: -0.0001

Data Index: 1514189 (Python Code)

Max Activating Token Index: 76

Text #2

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0959. Min Act: -0.0001

Data Index: 1390640 (Python Code)

Max Activating Token Index: 325

Text #3

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0956. Min Act: -0.0001

Data Index: 1643707 (Python Code)

Max Activating Token Index: 75

Text #4

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0952. Min Act: -0.0001

Data Index: 1656988 (Python Code)

Max Activating Token Index: 753

Text #5

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0902. Min Act: -0.0001

Data Index: 1433485 (Python Code)

Max Activating Token Index: 195

Text #6

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0988. Min Act: -0.0001

Data Index: 1537926 (Python Code)

Max Activating Token Index: 94

Text #7

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0958. Min Act: -0.0001

Data Index: 1431796 (Python Code)

Max Activating Token Index: 296

Text #8

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0961. Min Act: -0.0001

Data Index: 1391606 (Python Code)

Max Activating Token Index: 54

Text #9

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0957. Min Act: -0.0001

Data Index: 1615882 (Python Code)

Max Activating Token Index: 129

Text #10

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0924. Min Act: -0.0001

Data Index: 1510961 (Python Code)

Max Activating Token Index: 951

Text #11

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0957. Min Act: -0.0001

Data Index: 1588474 (Python Code)

Max Activating Token Index: 375

Text #12

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0960. Min Act: -0.0001

Data Index: 1399956 (Python Code)

Max Activating Token Index: 76

Text #13

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0911. Min Act: -0.0001

Data Index: 1598345 (Python Code)

Max Activating Token Index: 99

Text #14

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0885. Min Act: -0.0001

Data Index: 1385107 (Python Code)

Max Activating Token Index: 81

Text #15

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0879. Min Act: -0.0001

Data Index: 1367713 (Python Code)

Max Activating Token Index: 367

Text #16

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0935. Min Act: -0.0001

Data Index: 1618546 (Python Code)

Max Activating Token Index: 274

Text #17

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0934. Min Act: -0.0001

Data Index: 1419662 (Python Code)

Max Activating Token Index: 220

Text #18

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0896. Min Act: -0.0001

Data Index: 1474580 (Python Code)

Max Activating Token Index: 994

Text #19

Max Range: 0.1063. Min Range: -0.1063

Max Act: 0.0959. Min Act: -0.0001

Data Index: 1654357 (Python Code)

Max Activating Token Index: 170