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

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

Neuron 4311 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0133. Min Act: -0.0003

Data Index: 830717 (C4 (Web Text))

Max Activating Token Index: 77

Text #1

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0087. Min Act: -0.0003

Data Index: 813987 (C4 (Web Text))

Max Activating Token Index: 132

Text #2

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0079. Min Act: -0.0003

Data Index: 1102429 (C4 (Web Text))

Max Activating Token Index: 894

Text #3

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0077. Min Act: -0.0003

Data Index: 398422 (C4 (Web Text))

Max Activating Token Index: 118

Text #4

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0075. Min Act: -0.0003

Data Index: 822470 (C4 (Web Text))

Max Activating Token Index: 931

Text #5

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0077. Min Act: -0.0003

Data Index: 452078 (C4 (Web Text))

Max Activating Token Index: 102

Text #6

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0074. Min Act: -0.0003

Data Index: 231439 (C4 (Web Text))

Max Activating Token Index: 344

Text #7

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0073. Min Act: -0.0003

Data Index: 917060 (C4 (Web Text))

Max Activating Token Index: 386

Text #8

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0070. Min Act: -0.0002

Data Index: 556142 (C4 (Web Text))

Max Activating Token Index: 594

Text #9

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0073. Min Act: -0.0003

Data Index: 630635 (C4 (Web Text))

Max Activating Token Index: 135

Text #10

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0071. Min Act: -0.0003

Data Index: 948608 (C4 (Web Text))

Max Activating Token Index: 173

Text #11

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0072. Min Act: -0.0003

Data Index: 580835 (C4 (Web Text))

Max Activating Token Index: 572

Text #12

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0070. Min Act: -0.0003

Data Index: 591247 (C4 (Web Text))

Max Activating Token Index: 91

Text #13

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0071. Min Act: -0.0003

Data Index: 138499 (C4 (Web Text))

Max Activating Token Index: 210

Text #14

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0069. Min Act: -0.0003

Data Index: 993127 (C4 (Web Text))

Max Activating Token Index: 854

Text #15

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0068. Min Act: -0.0003

Data Index: 497302 (C4 (Web Text))

Max Activating Token Index: 420

Text #16

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0069. Min Act: -0.0003

Data Index: 1342007 (C4 (Web Text))

Max Activating Token Index: 103

Text #17

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0066. Min Act: -0.0003

Data Index: 268696 (C4 (Web Text))

Max Activating Token Index: 318

Text #18

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0070. Min Act: -0.0003

Data Index: 1218835 (C4 (Web Text))

Max Activating Token Index: 531

Text #19

Max Range: 0.0133. Min Range: -0.0133

Max Act: 0.0068. Min Act: -0.0003

Data Index: 1228603 (C4 (Web Text))

Max Activating Token Index: 587