Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1303 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0083. Min Act: -0.0003

Data Index: 1501900 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0064. Min Act: -0.0003

Data Index: 1482912 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0058. Min Act: -0.0003

Data Index: 1558477 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0053. Min Act: -0.0003

Data Index: 1043318 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0052. Min Act: -0.0003

Data Index: 204063 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0052. Min Act: -0.0003

Data Index: 779708 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0051. Min Act: -0.0003

Data Index: 1580174 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0048. Min Act: -0.0003

Data Index: 1373719 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0048. Min Act: -0.0003

Data Index: 1629083 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0046. Min Act: -0.0003

Data Index: 1398727 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0047. Min Act: -0.0003

Data Index: 1586096 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0046. Min Act: -0.0003

Data Index: 1472450 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0045. Min Act: -0.0003

Data Index: 369130 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0045. Min Act: -0.0003

Data Index: 1533025 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0043. Min Act: -0.0003

Data Index: 360040 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0044. Min Act: -0.0003

Data Index: 357144 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0044. Min Act: -0.0003

Data Index: 1209745 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0043. Min Act: -0.0003

Data Index: 260983 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0043. Min Act: -0.0003

Data Index: 1646394 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 0.0083. Min Range: -0.0083

Max Act: 0.0043. Min Act: -0.0003

Data Index: 1436337 (Python Code)

Max Activating Token Index: 1023