Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 2 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0090. Min Act: -0.0005

Data Index: 651119 (C4 (Web Text))

Max Activating Token Index: 979

Text #1

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0087. Min Act: -0.0005

Data Index: 15154 (C4 (Web Text))

Max Activating Token Index: 702

Text #2

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0086. Min Act: -0.0005

Data Index: 589809 (C4 (Web Text))

Max Activating Token Index: 42

Text #3

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0087. Min Act: -0.0005

Data Index: 844281 (C4 (Web Text))

Max Activating Token Index: 588

Text #4

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0085. Min Act: -0.0005

Data Index: 1316084 (C4 (Web Text))

Max Activating Token Index: 637

Text #5

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0086. Min Act: -0.0005

Data Index: 252426 (C4 (Web Text))

Max Activating Token Index: 219

Text #6

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0086. Min Act: -0.0005

Data Index: 732329 (C4 (Web Text))

Max Activating Token Index: 846

Text #7

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0085. Min Act: -0.0005

Data Index: 1171496 (C4 (Web Text))

Max Activating Token Index: 411

Text #8

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0083. Min Act: -0.0005

Data Index: 15487 (C4 (Web Text))

Max Activating Token Index: 671

Text #9

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0083. Min Act: -0.0006

Data Index: 1332704 (C4 (Web Text))

Max Activating Token Index: 589

Text #10

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0084. Min Act: -0.0005

Data Index: 655778 (C4 (Web Text))

Max Activating Token Index: 161

Text #11

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0083. Min Act: -0.0005

Data Index: 636932 (C4 (Web Text))

Max Activating Token Index: 145

Text #12

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0083. Min Act: -0.0005

Data Index: 1513122 (Python Code)

Max Activating Token Index: 161

Text #13

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0083. Min Act: -0.0006

Data Index: 1004459 (C4 (Web Text))

Max Activating Token Index: 24

Text #14

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0082. Min Act: -0.0005

Data Index: 845651 (C4 (Web Text))

Max Activating Token Index: 174

Text #15

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0082. Min Act: -0.0005

Data Index: 1172700 (C4 (Web Text))

Max Activating Token Index: 13

Text #16

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0081. Min Act: -0.0005

Data Index: 570417 (C4 (Web Text))

Max Activating Token Index: 204

Text #17

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0082. Min Act: -0.0005

Data Index: 599581 (C4 (Web Text))

Max Activating Token Index: 507

Text #18

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0082. Min Act: -0.0005

Data Index: 336465 (C4 (Web Text))

Max Activating Token Index: 828

Text #19

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0081. Min Act: -0.0005

Data Index: 911365 (C4 (Web Text))

Max Activating Token Index: 334