Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1329 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0143. Min Act: -0.0003

Data Index: 520685 (C4 (Web Text))

Max Activating Token Index: 997

Text #1

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0117. Min Act: -0.0003

Data Index: 1155300 (C4 (Web Text))

Max Activating Token Index: 770

Text #2

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0093. Min Act: -0.0005

Data Index: 195727 (C4 (Web Text))

Max Activating Token Index: 854

Text #3

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0089. Min Act: -0.0003

Data Index: 1331591 (C4 (Web Text))

Max Activating Token Index: 962

Text #4

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0087. Min Act: -0.0004

Data Index: 1577030 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0088. Min Act: -0.0003

Data Index: 76499 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0090. Min Act: -0.0004

Data Index: 259422 (C4 (Web Text))

Max Activating Token Index: 829

Text #7

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0087. Min Act: -0.0003

Data Index: 937648 (C4 (Web Text))

Max Activating Token Index: 735

Text #8

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0084. Min Act: -0.0004

Data Index: 139302 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0083. Min Act: -0.0004

Data Index: 1424553 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0083. Min Act: -0.0004

Data Index: 1079778 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0086. Min Act: -0.0004

Data Index: 1021418 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0082. Min Act: -0.0004

Data Index: 816757 (C4 (Web Text))

Max Activating Token Index: 790

Text #13

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0082. Min Act: -0.0005

Data Index: 178269 (C4 (Web Text))

Max Activating Token Index: 916

Text #14

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0083. Min Act: -0.0004

Data Index: 895693 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0082. Min Act: -0.0004

Data Index: 418790 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0079. Min Act: -0.0003

Data Index: 129399 (C4 (Web Text))

Max Activating Token Index: 797

Text #17

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0079. Min Act: -0.0004

Data Index: 1485101 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0075. Min Act: -0.0005

Data Index: 1415542 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 0.0143. Min Range: -0.0143

Max Act: 0.0078. Min Act: -0.0005

Data Index: 1582929 (Python Code)

Max Activating Token Index: 1023