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

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

Neuron 1095 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0069. Min Act: -0.0001

Data Index: 146895 (C4 (Web Text))

Max Activating Token Index: 221

Text #1

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0069. Min Act: -0.0001

Data Index: 85930 (C4 (Web Text))

Max Activating Token Index: 945

Text #2

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0066. Min Act: -0.0000

Data Index: 1538319 (Python Code)

Max Activating Token Index: 541

Text #3

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0068. Min Act: -0.0000

Data Index: 1424448 (Python Code)

Max Activating Token Index: 400

Text #4

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0061. Min Act: -0.0001

Data Index: 1582326 (Python Code)

Max Activating Token Index: 784

Text #5

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0066. Min Act: -0.0000

Data Index: 407421 (C4 (Web Text))

Max Activating Token Index: 841

Text #6

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0061. Min Act: -0.0000

Data Index: 1462184 (Python Code)

Max Activating Token Index: 368

Text #7

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0059. Min Act: -0.0001

Data Index: 349612 (C4 (Web Text))

Max Activating Token Index: 76

Text #8

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0064. Min Act: -0.0000

Data Index: 1439144 (Python Code)

Max Activating Token Index: 510

Text #9

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0059. Min Act: -0.0001

Data Index: 1419824 (Python Code)

Max Activating Token Index: 783

Text #10

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0059. Min Act: -0.0001

Data Index: 1448780 (Python Code)

Max Activating Token Index: 506

Text #11

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0058. Min Act: -0.0001

Data Index: 1421469 (Python Code)

Max Activating Token Index: 414

Text #12

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0057. Min Act: -0.0001

Data Index: 1502355 (Python Code)

Max Activating Token Index: 1004

Text #13

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0057. Min Act: -0.0000

Data Index: 1623903 (Python Code)

Max Activating Token Index: 805

Text #14

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0053. Min Act: -0.0001

Data Index: 923931 (C4 (Web Text))

Max Activating Token Index: 176

Text #15

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0054. Min Act: -0.0000

Data Index: 1440669 (Python Code)

Max Activating Token Index: 668

Text #16

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0056. Min Act: -0.0001

Data Index: 1216977 (C4 (Web Text))

Max Activating Token Index: 444

Text #17

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0056. Min Act: -0.0001

Data Index: 583737 (C4 (Web Text))

Max Activating Token Index: 559

Text #18

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0053. Min Act: -0.0001

Data Index: 1495827 (Python Code)

Max Activating Token Index: 736

Text #19

Max Range: 0.0069. Min Range: -0.0069

Max Act: 0.0052. Min Act: -0.0000

Data Index: 1238823 (C4 (Web Text))

Max Activating Token Index: 851