Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3204 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0091. Min Act: -0.0002

Data Index: 27418 (C4 (Web Text))

Max Activating Token Index: 655

Text #1

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0090. Min Act: -0.0002

Data Index: 698137 (C4 (Web Text))

Max Activating Token Index: 751

Text #2

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0083. Min Act: -0.0002

Data Index: 782218 (C4 (Web Text))

Max Activating Token Index: 216

Text #3

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0081. Min Act: -0.0002

Data Index: 1554159 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0081. Min Act: -0.0002

Data Index: 124286 (C4 (Web Text))

Max Activating Token Index: 94

Text #5

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0081. Min Act: -0.0002

Data Index: 997781 (C4 (Web Text))

Max Activating Token Index: 633

Text #6

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0081. Min Act: -0.0002

Data Index: 779794 (C4 (Web Text))

Max Activating Token Index: 584

Text #7

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0080. Min Act: -0.0002

Data Index: 308902 (C4 (Web Text))

Max Activating Token Index: 889

Text #8

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0079. Min Act: -0.0002

Data Index: 1371320 (Python Code)

Max Activating Token Index: 532

Text #9

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0079. Min Act: -0.0002

Data Index: 296176 (C4 (Web Text))

Max Activating Token Index: 654

Text #10

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0077. Min Act: -0.0002

Data Index: 385272 (C4 (Web Text))

Max Activating Token Index: 780

Text #11

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0078. Min Act: -0.0002

Data Index: 242914 (C4 (Web Text))

Max Activating Token Index: 313

Text #12

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0078. Min Act: -0.0002

Data Index: 740786 (C4 (Web Text))

Max Activating Token Index: 718

Text #13

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0078. Min Act: -0.0002

Data Index: 462536 (C4 (Web Text))

Max Activating Token Index: 96

Text #14

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0079. Min Act: -0.0002

Data Index: 1397922 (Python Code)

Max Activating Token Index: 63

Text #15

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0077. Min Act: -0.0002

Data Index: 683284 (C4 (Web Text))

Max Activating Token Index: 632

Text #16

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0076. Min Act: -0.0002

Data Index: 1579803 (Python Code)

Max Activating Token Index: 94

Text #17

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0076. Min Act: -0.0002

Data Index: 86190 (C4 (Web Text))

Max Activating Token Index: 854

Text #18

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0076. Min Act: -0.0002

Data Index: 178416 (C4 (Web Text))

Max Activating Token Index: 124

Text #19

Max Range: 0.0091. Min Range: -0.0091

Max Act: 0.0077. Min Act: -0.0002

Data Index: 16258 (C4 (Web Text))

Max Activating Token Index: 87