Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3921 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0849. Min Act: -0.0000

Data Index: 69097 (C4 (Web Text))

Max Activating Token Index: 730

Text #1

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0944. Min Act: 0.0000

Data Index: 472791 (C4 (Web Text))

Max Activating Token Index: 939

Text #2

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0820. Min Act: -0.0000

Data Index: 393742 (C4 (Web Text))

Max Activating Token Index: 804

Text #3

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0917. Min Act: -0.0000

Data Index: 1030202 (C4 (Web Text))

Max Activating Token Index: 987

Text #4

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0864. Min Act: -0.0000

Data Index: 619943 (C4 (Web Text))

Max Activating Token Index: 243

Text #5

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0793. Min Act: -0.0000

Data Index: 1307094 (C4 (Web Text))

Max Activating Token Index: 980

Text #6

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0810. Min Act: -0.0000

Data Index: 604107 (C4 (Web Text))

Max Activating Token Index: 249

Text #7

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0801. Min Act: -0.0000

Data Index: 437307 (C4 (Web Text))

Max Activating Token Index: 293

Text #8

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0776. Min Act: 0.0000

Data Index: 119767 (C4 (Web Text))

Max Activating Token Index: 498

Text #9

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0742. Min Act: -0.0000

Data Index: 1516252 (Python Code)

Max Activating Token Index: 199

Text #10

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0755. Min Act: 0.0000

Data Index: 418077 (C4 (Web Text))

Max Activating Token Index: 219

Text #11

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0782. Min Act: 0.0000

Data Index: 1427381 (Python Code)

Max Activating Token Index: 469

Text #12

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0755. Min Act: -0.0000

Data Index: 780200 (C4 (Web Text))

Max Activating Token Index: 302

Text #13

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0740. Min Act: -0.0000

Data Index: 1205155 (C4 (Web Text))

Max Activating Token Index: 86

Text #14

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0715. Min Act: -0.0000

Data Index: 45611 (C4 (Web Text))

Max Activating Token Index: 936

Text #15

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0705. Min Act: -0.0000

Data Index: 217990 (C4 (Web Text))

Max Activating Token Index: 78

Text #16

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0667. Min Act: -0.0000

Data Index: 1002301 (C4 (Web Text))

Max Activating Token Index: 859

Text #17

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0707. Min Act: -0.0000

Data Index: 1615055 (Python Code)

Max Activating Token Index: 134

Text #18

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0650. Min Act: -0.0000

Data Index: 1448136 (Python Code)

Max Activating Token Index: 893

Text #19

Max Range: 0.0944. Min Range: -0.0944

Max Act: 0.0720. Min Act: -0.0000

Data Index: 660586 (C4 (Web Text))

Max Activating Token Index: 211