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

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

Neuron 1347 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0080. Min Range: -0.0080

Max Act: 0.0080. Min Act: -0.0006

Data Index: 439098 (C4 (Web Text))

Max Activating Token Index: 759

Text #1

Max Range: 0.0080. Min Range: -0.0080

Max Act: 0.0080. Min Act: -0.0006

Data Index: 6781 (C4 (Web Text))

Max Activating Token Index: 139

Text #2

Max Range: 0.0080. Min Range: -0.0080

Max Act: 0.0076. Min Act: -0.0006

Data Index: 651033 (C4 (Web Text))

Max Activating Token Index: 247

Text #3

Max Range: 0.0080. Min Range: -0.0080

Max Act: 0.0072. Min Act: -0.0006

Data Index: 221454 (C4 (Web Text))

Max Activating Token Index: 1010

Text #4

Max Range: 0.0080. Min Range: -0.0080

Max Act: 0.0068. Min Act: -0.0006

Data Index: 733383 (C4 (Web Text))

Max Activating Token Index: 753

Text #5

Max Range: 0.0080. Min Range: -0.0080

Max Act: 0.0067. Min Act: -0.0006

Data Index: 1324444 (C4 (Web Text))

Max Activating Token Index: 662

Text #6

Max Range: 0.0080. Min Range: -0.0080

Max Act: 0.0072. Min Act: -0.0006

Data Index: 108276 (C4 (Web Text))

Max Activating Token Index: 899

Text #7

Max Range: 0.0080. Min Range: -0.0080

Max Act: 0.0069. Min Act: -0.0006

Data Index: 964598 (C4 (Web Text))

Max Activating Token Index: 794

Text #8

Max Range: 0.0080. Min Range: -0.0080

Max Act: 0.0070. Min Act: -0.0006

Data Index: 390195 (C4 (Web Text))

Max Activating Token Index: 854

Text #9

Max Range: 0.0080. Min Range: -0.0080

Max Act: 0.0072. Min Act: -0.0006

Data Index: 383466 (C4 (Web Text))

Max Activating Token Index: 91

Text #10

Max Range: 0.0080. Min Range: -0.0080

Max Act: 0.0069. Min Act: -0.0006

Data Index: 251757 (C4 (Web Text))

Max Activating Token Index: 619

Text #11

Max Range: 0.0080. Min Range: -0.0080

Max Act: 0.0070. Min Act: -0.0006

Data Index: 899560 (C4 (Web Text))

Max Activating Token Index: 283

Text #12

Max Range: 0.0080. Min Range: -0.0080

Max Act: 0.0067. Min Act: -0.0006

Data Index: 1282173 (C4 (Web Text))

Max Activating Token Index: 154

Text #13

Max Range: 0.0080. Min Range: -0.0080

Max Act: 0.0068. Min Act: -0.0006

Data Index: 188964 (C4 (Web Text))

Max Activating Token Index: 284

Text #14

Max Range: 0.0080. Min Range: -0.0080

Max Act: 0.0069. Min Act: -0.0005

Data Index: 1617720 (Python Code)

Max Activating Token Index: 215

Text #15

Max Range: 0.0080. Min Range: -0.0080

Max Act: 0.0062. Min Act: -0.0006

Data Index: 352997 (C4 (Web Text))

Max Activating Token Index: 657

Text #16

Max Range: 0.0080. Min Range: -0.0080

Max Act: 0.0065. Min Act: -0.0006

Data Index: 21578 (C4 (Web Text))

Max Activating Token Index: 318

Text #17

Max Range: 0.0080. Min Range: -0.0080

Max Act: 0.0067. Min Act: -0.0006

Data Index: 1114551 (C4 (Web Text))

Max Activating Token Index: 666

Text #18

Max Range: 0.0080. Min Range: -0.0080

Max Act: 0.0065. Min Act: -0.0006

Data Index: 266127 (C4 (Web Text))

Max Activating Token Index: 714

Text #19

Max Range: 0.0080. Min Range: -0.0080

Max Act: 0.0066. Min Act: -0.0006

Data Index: 72644 (C4 (Web Text))

Max Activating Token Index: 86