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

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

Neuron 445 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0090. Min Act: -0.0005

Data Index: 1388406 (Python Code)

Max Activating Token Index: 893

Text #1

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0086. Min Act: -0.0006

Data Index: 1205775 (C4 (Web Text))

Max Activating Token Index: 808

Text #2

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0086. Min Act: -0.0005

Data Index: 1651382 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0086. Min Act: -0.0006

Data Index: 617952 (C4 (Web Text))

Max Activating Token Index: 412

Text #4

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0082. Min Act: -0.0006

Data Index: 824081 (C4 (Web Text))

Max Activating Token Index: 748

Text #5

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0081. Min Act: -0.0006

Data Index: 356641 (C4 (Web Text))

Max Activating Token Index: 706

Text #6

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0081. Min Act: -0.0006

Data Index: 1289780 (C4 (Web Text))

Max Activating Token Index: 425

Text #7

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0079. Min Act: -0.0005

Data Index: 84357 (C4 (Web Text))

Max Activating Token Index: 112

Text #8

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0081. Min Act: -0.0006

Data Index: 1349597 (C4 (Web Text))

Max Activating Token Index: 551

Text #9

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0079. Min Act: -0.0006

Data Index: 1533592 (Python Code)

Max Activating Token Index: 395

Text #10

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0079. Min Act: -0.0006

Data Index: 187987 (C4 (Web Text))

Max Activating Token Index: 54

Text #11

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0079. Min Act: -0.0006

Data Index: 646668 (C4 (Web Text))

Max Activating Token Index: 340

Text #12

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0077. Min Act: -0.0006

Data Index: 1254400 (C4 (Web Text))

Max Activating Token Index: 678

Text #13

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0078. Min Act: -0.0006

Data Index: 258994 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0077. Min Act: -0.0006

Data Index: 701333 (C4 (Web Text))

Max Activating Token Index: 589

Text #15

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0076. Min Act: -0.0006

Data Index: 278738 (C4 (Web Text))

Max Activating Token Index: 382

Text #16

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0078. Min Act: -0.0005

Data Index: 1542806 (Python Code)

Max Activating Token Index: 155

Text #17

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0074. Min Act: -0.0005

Data Index: 1318496 (C4 (Web Text))

Max Activating Token Index: 661

Text #18

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0075. Min Act: -0.0006

Data Index: 111711 (C4 (Web Text))

Max Activating Token Index: 202

Text #19

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0075. Min Act: -0.0005

Data Index: 1490570 (Python Code)

Max Activating Token Index: 398