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

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

Neuron 2764 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: 0.0114. Min Range: -0.0114

Max Act: 0.0103. Min Act: -0.0003

Data Index: 467568 (C4 (Web Text))

Max Activating Token Index: 893

Text #1

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0114. Min Act: -0.0003

Data Index: 352578 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0087. Min Act: -0.0003

Data Index: 347934 (C4 (Web Text))

Max Activating Token Index: 303

Text #3

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0089. Min Act: -0.0003

Data Index: 666959 (C4 (Web Text))

Max Activating Token Index: 350

Text #4

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0087. Min Act: -0.0003

Data Index: 1029404 (C4 (Web Text))

Max Activating Token Index: 550

Text #5

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0094. Min Act: -0.0003

Data Index: 1050428 (C4 (Web Text))

Max Activating Token Index: 401

Text #6

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0085. Min Act: -0.0003

Data Index: 105710 (C4 (Web Text))

Max Activating Token Index: 853

Text #7

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0089. Min Act: -0.0003

Data Index: 1189823 (C4 (Web Text))

Max Activating Token Index: 424

Text #8

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0082. Min Act: -0.0003

Data Index: 1065567 (C4 (Web Text))

Max Activating Token Index: 1018

Text #9

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0087. Min Act: -0.0003

Data Index: 137169 (C4 (Web Text))

Max Activating Token Index: 29

Text #10

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0086. Min Act: -0.0003

Data Index: 610610 (C4 (Web Text))

Max Activating Token Index: 9

Text #11

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0085. Min Act: -0.0003

Data Index: 426755 (C4 (Web Text))

Max Activating Token Index: 445

Text #12

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0079. Min Act: -0.0003

Data Index: 466728 (C4 (Web Text))

Max Activating Token Index: 64

Text #13

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0087. Min Act: -0.0004

Data Index: 131799 (C4 (Web Text))

Max Activating Token Index: 629

Text #14

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0083. Min Act: -0.0003

Data Index: 642238 (C4 (Web Text))

Max Activating Token Index: 11

Text #15

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0078. Min Act: -0.0003

Data Index: 267803 (C4 (Web Text))

Max Activating Token Index: 629

Text #16

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0075. Min Act: -0.0003

Data Index: 995086 (C4 (Web Text))

Max Activating Token Index: 832

Text #17

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0076. Min Act: -0.0003

Data Index: 1056401 (C4 (Web Text))

Max Activating Token Index: 28

Text #18

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0087. Min Act: -0.0003

Data Index: 207971 (C4 (Web Text))

Max Activating Token Index: 289

Text #19

Max Range: 0.0114. Min Range: -0.0114

Max Act: 0.0072. Min Act: -0.0003

Data Index: 224566 (C4 (Web Text))

Max Activating Token Index: 339