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

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

Neuron 2700 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0077. Min Act: -0.0001

Data Index: 746831 (C4 (Web Text))

Max Activating Token Index: 79

Text #1

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0070. Min Act: -0.0001

Data Index: 943051 (C4 (Web Text))

Max Activating Token Index: 60

Text #2

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0076. Min Act: -0.0001

Data Index: 939795 (C4 (Web Text))

Max Activating Token Index: 260

Text #3

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0066. Min Act: -0.0001

Data Index: 682996 (C4 (Web Text))

Max Activating Token Index: 172

Text #4

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0068. Min Act: -0.0001

Data Index: 1519838 (Python Code)

Max Activating Token Index: 193

Text #5

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0066. Min Act: -0.0001

Data Index: 873717 (C4 (Web Text))

Max Activating Token Index: 136

Text #6

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0067. Min Act: -0.0001

Data Index: 428233 (C4 (Web Text))

Max Activating Token Index: 146

Text #7

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0067. Min Act: -0.0001

Data Index: 854993 (C4 (Web Text))

Max Activating Token Index: 100

Text #8

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0066. Min Act: -0.0001

Data Index: 240899 (C4 (Web Text))

Max Activating Token Index: 146

Text #9

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0063. Min Act: -0.0001

Data Index: 32645 (C4 (Web Text))

Max Activating Token Index: 123

Text #10

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0062. Min Act: -0.0001

Data Index: 908083 (C4 (Web Text))

Max Activating Token Index: 418

Text #11

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0065. Min Act: -0.0001

Data Index: 185124 (C4 (Web Text))

Max Activating Token Index: 185

Text #12

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0063. Min Act: -0.0001

Data Index: 475088 (C4 (Web Text))

Max Activating Token Index: 275

Text #13

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0062. Min Act: -0.0001

Data Index: 1429209 (Python Code)

Max Activating Token Index: 152

Text #14

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0064. Min Act: -0.0001

Data Index: 1400976 (Python Code)

Max Activating Token Index: 78

Text #15

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0062. Min Act: -0.0001

Data Index: 219861 (C4 (Web Text))

Max Activating Token Index: 27

Text #16

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0065. Min Act: -0.0001

Data Index: 1588107 (Python Code)

Max Activating Token Index: 247

Text #17

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0065. Min Act: -0.0001

Data Index: 1556032 (Python Code)

Max Activating Token Index: 138

Text #18

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0062. Min Act: -0.0001

Data Index: 32648 (C4 (Web Text))

Max Activating Token Index: 72

Text #19

Max Range: 0.0077. Min Range: -0.0077

Max Act: 0.0062. Min Act: -0.0001

Data Index: 300340 (C4 (Web Text))

Max Activating Token Index: 80