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

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

Neuron 1701 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0038. Min Act: -0.0002

Data Index: 409782 (C4 (Web Text))

Max Activating Token Index: 943

Text #1

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0036. Min Act: -0.0002

Data Index: 366549 (C4 (Web Text))

Max Activating Token Index: 937

Text #2

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0035. Min Act: -0.0002

Data Index: 1182450 (C4 (Web Text))

Max Activating Token Index: 1007

Text #3

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0035. Min Act: -0.0002

Data Index: 144150 (C4 (Web Text))

Max Activating Token Index: 897

Text #4

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0035. Min Act: -0.0002

Data Index: 682003 (C4 (Web Text))

Max Activating Token Index: 957

Text #5

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0034. Min Act: -0.0002

Data Index: 1176604 (C4 (Web Text))

Max Activating Token Index: 989

Text #6

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0033. Min Act: -0.0002

Data Index: 1291704 (C4 (Web Text))

Max Activating Token Index: 964

Text #7

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0033. Min Act: -0.0002

Data Index: 958865 (C4 (Web Text))

Max Activating Token Index: 930

Text #8

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0033. Min Act: -0.0002

Data Index: 381809 (C4 (Web Text))

Max Activating Token Index: 946

Text #9

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0032. Min Act: -0.0002

Data Index: 276544 (C4 (Web Text))

Max Activating Token Index: 930

Text #10

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0032. Min Act: -0.0002

Data Index: 598510 (C4 (Web Text))

Max Activating Token Index: 973

Text #11

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0032. Min Act: -0.0002

Data Index: 1274840 (C4 (Web Text))

Max Activating Token Index: 997

Text #12

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0032. Min Act: -0.0002

Data Index: 883760 (C4 (Web Text))

Max Activating Token Index: 944

Text #13

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0032. Min Act: -0.0002

Data Index: 1066373 (C4 (Web Text))

Max Activating Token Index: 921

Text #14

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0032. Min Act: -0.0002

Data Index: 1315925 (C4 (Web Text))

Max Activating Token Index: 993

Text #15

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0031. Min Act: -0.0002

Data Index: 839994 (C4 (Web Text))

Max Activating Token Index: 967

Text #16

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0032. Min Act: -0.0002

Data Index: 202305 (C4 (Web Text))

Max Activating Token Index: 989

Text #17

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0032. Min Act: -0.0002

Data Index: 250867 (C4 (Web Text))

Max Activating Token Index: 964

Text #18

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0031. Min Act: -0.0002

Data Index: 806695 (C4 (Web Text))

Max Activating Token Index: 944

Text #19

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0031. Min Act: -0.0002

Data Index: 478981 (C4 (Web Text))

Max Activating Token Index: 958