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

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

Neuron 639 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0102. Min Act: -0.0004

Data Index: 1286870 (C4 (Web Text))

Max Activating Token Index: 750

Text #1

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0095. Min Act: -0.0004

Data Index: 1522010 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0080. Min Act: -0.0004

Data Index: 221283 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0082. Min Act: -0.0004

Data Index: 1032329 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0083. Min Act: -0.0004

Data Index: 1246761 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0063. Min Act: -0.0004

Data Index: 293672 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0066. Min Act: -0.0004

Data Index: 280293 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0069. Min Act: -0.0004

Data Index: 430341 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0052. Min Act: -0.0004

Data Index: 622059 (C4 (Web Text))

Max Activating Token Index: 334

Text #9

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0071. Min Act: -0.0004

Data Index: 539551 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0068. Min Act: -0.0004

Data Index: 1308349 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0064. Min Act: -0.0004

Data Index: 483745 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0066. Min Act: -0.0004

Data Index: 897630 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0064. Min Act: -0.0004

Data Index: 623495 (C4 (Web Text))

Max Activating Token Index: 112

Text #14

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0050. Min Act: -0.0004

Data Index: 1235109 (C4 (Web Text))

Max Activating Token Index: 554

Text #15

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0068. Min Act: -0.0004

Data Index: 1317583 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0067. Min Act: -0.0004

Data Index: 1166475 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0048. Min Act: -0.0004

Data Index: 848915 (C4 (Web Text))

Max Activating Token Index: 652

Text #18

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0074. Min Act: -0.0004

Data Index: 998967 (C4 (Web Text))

Max Activating Token Index: 67

Text #19

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0063. Min Act: -0.0004

Data Index: 468265 (C4 (Web Text))

Max Activating Token Index: 1023