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

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

Neuron 3878 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0164. Min Act: -0.0003

Data Index: 1578407 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0088. Min Act: -0.0003

Data Index: 1464286 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0074. Min Act: -0.0003

Data Index: 712640 (C4 (Web Text))

Max Activating Token Index: 356

Text #3

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0083. Min Act: -0.0003

Data Index: 1575818 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0082. Min Act: -0.0003

Data Index: 1631962 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0072. Min Act: -0.0003

Data Index: 1457493 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0074. Min Act: -0.0003

Data Index: 462288 (C4 (Web Text))

Max Activating Token Index: 546

Text #7

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0087. Min Act: -0.0003

Data Index: 1410596 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0060. Min Act: -0.0003

Data Index: 1167886 (C4 (Web Text))

Max Activating Token Index: 689

Text #9

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0066. Min Act: -0.0003

Data Index: 1407736 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0072. Min Act: -0.0003

Data Index: 1171822 (C4 (Web Text))

Max Activating Token Index: 505

Text #11

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0075. Min Act: -0.0003

Data Index: 1461954 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0064. Min Act: -0.0003

Data Index: 1472560 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0067. Min Act: -0.0003

Data Index: 1519552 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0064. Min Act: -0.0003

Data Index: 1553895 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0067. Min Act: -0.0003

Data Index: 877209 (C4 (Web Text))

Max Activating Token Index: 966

Text #16

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0055. Min Act: -0.0003

Data Index: 1544318 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0061. Min Act: -0.0003

Data Index: 1448804 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0068. Min Act: -0.0003

Data Index: 632829 (C4 (Web Text))

Max Activating Token Index: 998

Text #19

Max Range: 0.0164. Min Range: -0.0164

Max Act: 0.0063. Min Act: -0.0003

Data Index: 371898 (C4 (Web Text))

Max Activating Token Index: 958