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

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

Neuron 1532 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: 0.0078. Min Range: -0.0078

Max Act: 0.0078. Min Act: -0.0006

Data Index: 433882 (C4 (Web Text))

Max Activating Token Index: 93

Text #1

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0074. Min Act: -0.0006

Data Index: 295273 (C4 (Web Text))

Max Activating Token Index: 158

Text #2

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0071. Min Act: -0.0006

Data Index: 1238446 (C4 (Web Text))

Max Activating Token Index: 850

Text #3

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0069. Min Act: -0.0006

Data Index: 329642 (C4 (Web Text))

Max Activating Token Index: 515

Text #4

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0069. Min Act: -0.0006

Data Index: 919757 (C4 (Web Text))

Max Activating Token Index: 314

Text #5

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0068. Min Act: -0.0006

Data Index: 452150 (C4 (Web Text))

Max Activating Token Index: 951

Text #6

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0068. Min Act: -0.0006

Data Index: 391401 (C4 (Web Text))

Max Activating Token Index: 354

Text #7

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0067. Min Act: -0.0006

Data Index: 488124 (C4 (Web Text))

Max Activating Token Index: 843

Text #8

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0067. Min Act: -0.0006

Data Index: 1045479 (C4 (Web Text))

Max Activating Token Index: 969

Text #9

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0067. Min Act: -0.0006

Data Index: 1619334 (Python Code)

Max Activating Token Index: 455

Text #10

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0067. Min Act: -0.0006

Data Index: 143682 (C4 (Web Text))

Max Activating Token Index: 260

Text #11

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0065. Min Act: -0.0006

Data Index: 461160 (C4 (Web Text))

Max Activating Token Index: 859

Text #12

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0064. Min Act: -0.0006

Data Index: 307607 (C4 (Web Text))

Max Activating Token Index: 985

Text #13

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0065. Min Act: -0.0006

Data Index: 750398 (C4 (Web Text))

Max Activating Token Index: 903

Text #14

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0065. Min Act: -0.0006

Data Index: 1223257 (C4 (Web Text))

Max Activating Token Index: 487

Text #15

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0065. Min Act: -0.0006

Data Index: 677309 (C4 (Web Text))

Max Activating Token Index: 214

Text #16

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0065. Min Act: -0.0006

Data Index: 1509439 (Python Code)

Max Activating Token Index: 1001

Text #17

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0064. Min Act: -0.0006

Data Index: 579109 (C4 (Web Text))

Max Activating Token Index: 907

Text #18

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0065. Min Act: -0.0006

Data Index: 354441 (C4 (Web Text))

Max Activating Token Index: 332

Text #19

Max Range: 0.0078. Min Range: -0.0078

Max Act: 0.0064. Min Act: -0.0006

Data Index: 20069 (C4 (Web Text))

Max Activating Token Index: 349