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

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

Neuron 2744 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.1160. Min Act: -0.0001

Data Index: 336292 (C4 (Web Text))

Max Activating Token Index: 752

Text #1

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.1104. Min Act: -0.0001

Data Index: 1157565 (C4 (Web Text))

Max Activating Token Index: 739

Text #2

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0977. Min Act: -0.0001

Data Index: 800744 (C4 (Web Text))

Max Activating Token Index: 961

Text #3

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0901. Min Act: -0.0001

Data Index: 293208 (C4 (Web Text))

Max Activating Token Index: 194

Text #4

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0953. Min Act: -0.0001

Data Index: 137369 (C4 (Web Text))

Max Activating Token Index: 109

Text #5

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0976. Min Act: -0.0001

Data Index: 1144836 (C4 (Web Text))

Max Activating Token Index: 1016

Text #6

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0896. Min Act: -0.0001

Data Index: 1286329 (C4 (Web Text))

Max Activating Token Index: 696

Text #7

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0929. Min Act: -0.0001

Data Index: 1656795 (Python Code)

Max Activating Token Index: 940

Text #8

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0984. Min Act: -0.0001

Data Index: 726075 (C4 (Web Text))

Max Activating Token Index: 618

Text #9

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0936. Min Act: -0.0001

Data Index: 1575272 (Python Code)

Max Activating Token Index: 619

Text #10

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0866. Min Act: -0.0001

Data Index: 921621 (C4 (Web Text))

Max Activating Token Index: 115

Text #11

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0870. Min Act: -0.0001

Data Index: 317474 (C4 (Web Text))

Max Activating Token Index: 895

Text #12

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0919. Min Act: -0.0001

Data Index: 232932 (C4 (Web Text))

Max Activating Token Index: 730

Text #13

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0880. Min Act: -0.0001

Data Index: 1605899 (Python Code)

Max Activating Token Index: 1003

Text #14

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0885. Min Act: -0.0001

Data Index: 882570 (C4 (Web Text))

Max Activating Token Index: 732

Text #15

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0846. Min Act: -0.0001

Data Index: 986409 (C4 (Web Text))

Max Activating Token Index: 106

Text #16

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0898. Min Act: -0.0001

Data Index: 1299500 (C4 (Web Text))

Max Activating Token Index: 128

Text #17

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0834. Min Act: -0.0001

Data Index: 966573 (C4 (Web Text))

Max Activating Token Index: 112

Text #18

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0870. Min Act: -0.0001

Data Index: 598639 (C4 (Web Text))

Max Activating Token Index: 884

Text #19

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0867. Min Act: -0.0001

Data Index: 1370003 (Python Code)

Max Activating Token Index: 562