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

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

Neuron 601 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0094. Min Act: -0.0005

Data Index: 1379981 (Python Code)

Max Activating Token Index: 257

Text #1

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0093. Min Act: -0.0005

Data Index: 1501702 (Python Code)

Max Activating Token Index: 322

Text #2

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0087. Min Act: -0.0005

Data Index: 1453860 (Python Code)

Max Activating Token Index: 140

Text #3

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0085. Min Act: -0.0005

Data Index: 1427715 (Python Code)

Max Activating Token Index: 70

Text #4

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0082. Min Act: -0.0005

Data Index: 992543 (C4 (Web Text))

Max Activating Token Index: 444

Text #5

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0080. Min Act: -0.0005

Data Index: 471731 (C4 (Web Text))

Max Activating Token Index: 268

Text #6

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0081. Min Act: -0.0005

Data Index: 368215 (C4 (Web Text))

Max Activating Token Index: 181

Text #7

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0081. Min Act: -0.0005

Data Index: 236525 (C4 (Web Text))

Max Activating Token Index: 508

Text #8

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0077. Min Act: -0.0005

Data Index: 1593908 (Python Code)

Max Activating Token Index: 445

Text #9

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0080. Min Act: -0.0005

Data Index: 713340 (C4 (Web Text))

Max Activating Token Index: 848

Text #10

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0078. Min Act: -0.0005

Data Index: 1506247 (Python Code)

Max Activating Token Index: 332

Text #11

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0078. Min Act: -0.0006

Data Index: 890964 (C4 (Web Text))

Max Activating Token Index: 251

Text #12

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0076. Min Act: -0.0005

Data Index: 276765 (C4 (Web Text))

Max Activating Token Index: 288

Text #13

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0077. Min Act: -0.0005

Data Index: 450837 (C4 (Web Text))

Max Activating Token Index: 756

Text #14

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0078. Min Act: -0.0005

Data Index: 113133 (C4 (Web Text))

Max Activating Token Index: 822

Text #15

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0077. Min Act: -0.0005

Data Index: 472637 (C4 (Web Text))

Max Activating Token Index: 21

Text #16

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0078. Min Act: -0.0005

Data Index: 1122938 (C4 (Web Text))

Max Activating Token Index: 687

Text #17

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0077. Min Act: -0.0005

Data Index: 1378855 (Python Code)

Max Activating Token Index: 243

Text #18

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0076. Min Act: -0.0005

Data Index: 435625 (C4 (Web Text))

Max Activating Token Index: 973

Text #19

Max Range: 0.0094. Min Range: -0.0094

Max Act: 0.0077. Min Act: -0.0006

Data Index: 571997 (C4 (Web Text))

Max Activating Token Index: 746