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

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

Neuron 2092 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: 0.0091. Min Range: -0.0091

Max Act: 0.0086. Min Act: -0.0003

Data Index: 86167 (C4 (Web Text))

Max Activating Token Index: 10

Text #1

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0091. Min Act: -0.0003

Data Index: 1246453 (C4 (Web Text))

Max Activating Token Index: 476

Text #2

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0070. Min Act: -0.0003

Data Index: 1333721 (C4 (Web Text))

Max Activating Token Index: 266

Text #3

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0073. Min Act: -0.0003

Data Index: 514032 (C4 (Web Text))

Max Activating Token Index: 10

Text #4

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0070. Min Act: -0.0003

Data Index: 1198086 (C4 (Web Text))

Max Activating Token Index: 412

Text #5

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0069. Min Act: -0.0003

Data Index: 195505 (C4 (Web Text))

Max Activating Token Index: 82

Text #6

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0065. Min Act: -0.0003

Data Index: 619930 (C4 (Web Text))

Max Activating Token Index: 612

Text #7

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0069. Min Act: -0.0003

Data Index: 252755 (C4 (Web Text))

Max Activating Token Index: 591

Text #8

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0065. Min Act: -0.0003

Data Index: 1309077 (C4 (Web Text))

Max Activating Token Index: 29

Text #9

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0064. Min Act: -0.0003

Data Index: 367743 (C4 (Web Text))

Max Activating Token Index: 657

Text #10

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0064. Min Act: -0.0003

Data Index: 486402 (C4 (Web Text))

Max Activating Token Index: 22

Text #11

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0062. Min Act: -0.0003

Data Index: 949088 (C4 (Web Text))

Max Activating Token Index: 1006

Text #12

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0060. Min Act: -0.0003

Data Index: 119915 (C4 (Web Text))

Max Activating Token Index: 104

Text #13

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0065. Min Act: -0.0003

Data Index: 580126 (C4 (Web Text))

Max Activating Token Index: 517

Text #14

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0056. Min Act: -0.0003

Data Index: 1517942 (Python Code)

Max Activating Token Index: 174

Text #15

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0060. Min Act: -0.0003

Data Index: 190035 (C4 (Web Text))

Max Activating Token Index: 935

Text #16

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0057. Min Act: -0.0003

Data Index: 1146635 (C4 (Web Text))

Max Activating Token Index: 910

Text #17

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0057. Min Act: -0.0003

Data Index: 1264288 (C4 (Web Text))

Max Activating Token Index: 898

Text #18

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0059. Min Act: -0.0003

Data Index: 662614 (C4 (Web Text))

Max Activating Token Index: 189

Text #19

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0058. Min Act: -0.0003

Data Index: 796302 (C4 (Web Text))

Max Activating Token Index: 707