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

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

Neuron 2804 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7908. Min Range: -0.7908

Max Act: 0.7908. Min Act: -0.0000

Data Index: 1580805 (Python Code)

Max Activating Token Index: 699

Text #1

Max Range: 0.7908. Min Range: -0.7908

Max Act: 0.6918. Min Act: -0.0000

Data Index: 297820 (C4 (Web Text))

Max Activating Token Index: 616

Text #2

Max Range: 0.7908. Min Range: -0.7908

Max Act: 0.6677. Min Act: -0.0000

Data Index: 1132538 (C4 (Web Text))

Max Activating Token Index: 283

Text #3

Max Range: 0.7908. Min Range: -0.7908

Max Act: 0.6411. Min Act: -0.0000

Data Index: 1439147 (Python Code)

Max Activating Token Index: 973

Text #4

Max Range: 0.7908. Min Range: -0.7908

Max Act: 0.6531. Min Act: -0.0000

Data Index: 1387653 (Python Code)

Max Activating Token Index: 649

Text #5

Max Range: 0.7908. Min Range: -0.7908

Max Act: 0.6189. Min Act: -0.0000

Data Index: 1548563 (Python Code)

Max Activating Token Index: 712

Text #6

Max Range: 0.7908. Min Range: -0.7908

Max Act: 0.6119. Min Act: -0.0000

Data Index: 522125 (C4 (Web Text))

Max Activating Token Index: 208

Text #7

Max Range: 0.7908. Min Range: -0.7908

Max Act: 0.6033. Min Act: -0.0000

Data Index: 912369 (C4 (Web Text))

Max Activating Token Index: 641

Text #8

Max Range: 0.7908. Min Range: -0.7908

Max Act: 0.6176. Min Act: -0.0000

Data Index: 480860 (C4 (Web Text))

Max Activating Token Index: 417

Text #9

Max Range: 0.7908. Min Range: -0.7908

Max Act: 0.6157. Min Act: -0.0000

Data Index: 786033 (C4 (Web Text))

Max Activating Token Index: 599

Text #10

Max Range: 0.7908. Min Range: -0.7908

Max Act: 0.5921. Min Act: -0.0000

Data Index: 1591767 (Python Code)

Max Activating Token Index: 87

Text #11

Max Range: 0.7908. Min Range: -0.7908

Max Act: 0.5719. Min Act: -0.0000

Data Index: 1625685 (Python Code)

Max Activating Token Index: 483

Text #12

Max Range: 0.7908. Min Range: -0.7908

Max Act: 0.5641. Min Act: -0.0000

Data Index: 281839 (C4 (Web Text))

Max Activating Token Index: 325

Text #13

Max Range: 0.7908. Min Range: -0.7908

Max Act: 0.5174. Min Act: -0.0000

Data Index: 1652904 (Python Code)

Max Activating Token Index: 894

Text #14

Max Range: 0.7908. Min Range: -0.7908

Max Act: 0.5740. Min Act: -0.0000

Data Index: 1447142 (Python Code)

Max Activating Token Index: 78

Text #15

Max Range: 0.7908. Min Range: -0.7908

Max Act: 0.5752. Min Act: -0.0000

Data Index: 858243 (C4 (Web Text))

Max Activating Token Index: 340

Text #16

Max Range: 0.7908. Min Range: -0.7908

Max Act: 0.5737. Min Act: -0.0000

Data Index: 1433301 (Python Code)

Max Activating Token Index: 499

Text #17

Max Range: 0.7908. Min Range: -0.7908

Max Act: 0.5707. Min Act: -0.0000

Data Index: 751950 (C4 (Web Text))

Max Activating Token Index: 157

Text #18

Max Range: 0.7908. Min Range: -0.7908

Max Act: 0.5811. Min Act: -0.0000

Data Index: 568206 (C4 (Web Text))

Max Activating Token Index: 130

Text #19

Max Range: 0.7908. Min Range: -0.7908

Max Act: 0.5401. Min Act: -0.0000

Data Index: 1542755 (Python Code)

Max Activating Token Index: 616