Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1780 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0088. Min Act: -0.0003

Data Index: 547332 (C4 (Web Text))

Max Activating Token Index: 771

Text #1

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0087. Min Act: -0.0003

Data Index: 36588 (C4 (Web Text))

Max Activating Token Index: 150

Text #2

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0083. Min Act: -0.0003

Data Index: 1091868 (C4 (Web Text))

Max Activating Token Index: 149

Text #3

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0081. Min Act: -0.0003

Data Index: 763841 (C4 (Web Text))

Max Activating Token Index: 35

Text #4

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0081. Min Act: -0.0003

Data Index: 1288218 (C4 (Web Text))

Max Activating Token Index: 142

Text #5

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0081. Min Act: -0.0002

Data Index: 925156 (C4 (Web Text))

Max Activating Token Index: 374

Text #6

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0080. Min Act: -0.0003

Data Index: 9656 (C4 (Web Text))

Max Activating Token Index: 730

Text #7

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0079. Min Act: -0.0003

Data Index: 726747 (C4 (Web Text))

Max Activating Token Index: 318

Text #8

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0079. Min Act: -0.0003

Data Index: 1280577 (C4 (Web Text))

Max Activating Token Index: 33

Text #9

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0078. Min Act: -0.0003

Data Index: 262041 (C4 (Web Text))

Max Activating Token Index: 772

Text #10

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0078. Min Act: -0.0003

Data Index: 408659 (C4 (Web Text))

Max Activating Token Index: 669

Text #11

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0077. Min Act: -0.0003

Data Index: 663297 (C4 (Web Text))

Max Activating Token Index: 442

Text #12

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0078. Min Act: -0.0003

Data Index: 230875 (C4 (Web Text))

Max Activating Token Index: 797

Text #13

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0077. Min Act: -0.0003

Data Index: 871665 (C4 (Web Text))

Max Activating Token Index: 350

Text #14

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0077. Min Act: -0.0003

Data Index: 1272246 (C4 (Web Text))

Max Activating Token Index: 618

Text #15

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0077. Min Act: -0.0003

Data Index: 796379 (C4 (Web Text))

Max Activating Token Index: 610

Text #16

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0077. Min Act: -0.0003

Data Index: 44323 (C4 (Web Text))

Max Activating Token Index: 536

Text #17

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0075. Min Act: -0.0003

Data Index: 1124263 (C4 (Web Text))

Max Activating Token Index: 792

Text #18

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0077. Min Act: -0.0003

Data Index: 156696 (C4 (Web Text))

Max Activating Token Index: 673

Text #19

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0077. Min Act: -0.0003

Data Index: 1284331 (C4 (Web Text))

Max Activating Token Index: 170