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

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

Neuron 1103 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0064. Min Act: -0.0003

Data Index: 1145629 (C4 (Web Text))

Max Activating Token Index: 132

Text #1

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0061. Min Act: -0.0003

Data Index: 795507 (C4 (Web Text))

Max Activating Token Index: 117

Text #2

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0062. Min Act: -0.0003

Data Index: 521402 (C4 (Web Text))

Max Activating Token Index: 35

Text #3

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0059. Min Act: -0.0003

Data Index: 1240863 (C4 (Web Text))

Max Activating Token Index: 142

Text #4

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0060. Min Act: -0.0003

Data Index: 1352938 (C4 (Web Text))

Max Activating Token Index: 15

Text #5

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0059. Min Act: -0.0003

Data Index: 498963 (C4 (Web Text))

Max Activating Token Index: 34

Text #6

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0055. Min Act: -0.0003

Data Index: 1170161 (C4 (Web Text))

Max Activating Token Index: 106

Text #7

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0053. Min Act: -0.0003

Data Index: 845086 (C4 (Web Text))

Max Activating Token Index: 73

Text #8

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0053. Min Act: -0.0003

Data Index: 1324120 (C4 (Web Text))

Max Activating Token Index: 24

Text #9

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0054. Min Act: -0.0003

Data Index: 720387 (C4 (Web Text))

Max Activating Token Index: 92

Text #10

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0054. Min Act: -0.0003

Data Index: 1078136 (C4 (Web Text))

Max Activating Token Index: 132

Text #11

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0051. Min Act: -0.0003

Data Index: 308167 (C4 (Web Text))

Max Activating Token Index: 62

Text #12

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0052. Min Act: -0.0003

Data Index: 579766 (C4 (Web Text))

Max Activating Token Index: 112

Text #13

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0054. Min Act: -0.0003

Data Index: 234245 (C4 (Web Text))

Max Activating Token Index: 11

Text #14

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0051. Min Act: -0.0002

Data Index: 673516 (C4 (Web Text))

Max Activating Token Index: 120

Text #15

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0048. Min Act: -0.0002

Data Index: 800561 (C4 (Web Text))

Max Activating Token Index: 62

Text #16

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0051. Min Act: -0.0002

Data Index: 634081 (C4 (Web Text))

Max Activating Token Index: 51

Text #17

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0048. Min Act: -0.0003

Data Index: 1081582 (C4 (Web Text))

Max Activating Token Index: 23

Text #18

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0052. Min Act: -0.0003

Data Index: 72728 (C4 (Web Text))

Max Activating Token Index: 67

Text #19

Max Range: 0.0064. Min Range: -0.0064

Max Act: 0.0048. Min Act: -0.0003

Data Index: 899219 (C4 (Web Text))

Max Activating Token Index: 53