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

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

Neuron 880 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1165. Min Range: -0.1165

Max Act: 0.1165. Min Act: -0.0006

Data Index: 1196081 (C4 (Web Text))

Max Activating Token Index: 863

Text #1

Max Range: 0.1165. Min Range: -0.1165

Max Act: 0.1148. Min Act: -0.0006

Data Index: 98975 (C4 (Web Text))

Max Activating Token Index: 692

Text #2

Max Range: 0.1165. Min Range: -0.1165

Max Act: 0.1088. Min Act: -0.0006

Data Index: 1118820 (C4 (Web Text))

Max Activating Token Index: 765

Text #3

Max Range: 0.1165. Min Range: -0.1165

Max Act: 0.1073. Min Act: -0.0006

Data Index: 575282 (C4 (Web Text))

Max Activating Token Index: 710

Text #4

Max Range: 0.1165. Min Range: -0.1165

Max Act: 0.1025. Min Act: -0.0006

Data Index: 584170 (C4 (Web Text))

Max Activating Token Index: 294

Text #5

Max Range: 0.1165. Min Range: -0.1165

Max Act: 0.0984. Min Act: -0.0006

Data Index: 652503 (C4 (Web Text))

Max Activating Token Index: 652

Text #6

Max Range: 0.1165. Min Range: -0.1165

Max Act: 0.1014. Min Act: -0.0006

Data Index: 1225178 (C4 (Web Text))

Max Activating Token Index: 940

Text #7

Max Range: 0.1165. Min Range: -0.1165

Max Act: 0.1000. Min Act: -0.0006

Data Index: 332564 (C4 (Web Text))

Max Activating Token Index: 200

Text #8

Max Range: 0.1165. Min Range: -0.1165

Max Act: 0.0958. Min Act: -0.0006

Data Index: 331669 (C4 (Web Text))

Max Activating Token Index: 926

Text #9

Max Range: 0.1165. Min Range: -0.1165

Max Act: 0.0994. Min Act: -0.0006

Data Index: 821130 (C4 (Web Text))

Max Activating Token Index: 561

Text #10

Max Range: 0.1165. Min Range: -0.1165

Max Act: 0.0980. Min Act: -0.0006

Data Index: 825361 (C4 (Web Text))

Max Activating Token Index: 80

Text #11

Max Range: 0.1165. Min Range: -0.1165

Max Act: 0.0968. Min Act: -0.0006

Data Index: 448504 (C4 (Web Text))

Max Activating Token Index: 328

Text #12

Max Range: 0.1165. Min Range: -0.1165

Max Act: 0.0960. Min Act: -0.0006

Data Index: 710683 (C4 (Web Text))

Max Activating Token Index: 875

Text #13

Max Range: 0.1165. Min Range: -0.1165

Max Act: 0.0991. Min Act: -0.0006

Data Index: 409327 (C4 (Web Text))

Max Activating Token Index: 223

Text #14

Max Range: 0.1165. Min Range: -0.1165

Max Act: 0.0953. Min Act: -0.0006

Data Index: 654199 (C4 (Web Text))

Max Activating Token Index: 633

Text #15

Max Range: 0.1165. Min Range: -0.1165

Max Act: 0.0949. Min Act: -0.0006

Data Index: 1241363 (C4 (Web Text))

Max Activating Token Index: 921

Text #16

Max Range: 0.1165. Min Range: -0.1165

Max Act: 0.0912. Min Act: -0.0006

Data Index: 185369 (C4 (Web Text))

Max Activating Token Index: 769

Text #17

Max Range: 0.1165. Min Range: -0.1165

Max Act: 0.0947. Min Act: -0.0005

Data Index: 1255072 (C4 (Web Text))

Max Activating Token Index: 351

Text #18

Max Range: 0.1165. Min Range: -0.1165

Max Act: 0.0948. Min Act: -0.0006

Data Index: 703676 (C4 (Web Text))

Max Activating Token Index: 775

Text #19

Max Range: 0.1165. Min Range: -0.1165

Max Act: 0.0947. Min Act: -0.0006

Data Index: 734668 (C4 (Web Text))

Max Activating Token Index: 116