Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4155 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.0454. Min Range: -1.0454

Max Act: 1.0454. Min Act: -0.0000

Data Index: 589076 (C4 (Web Text))

Max Activating Token Index: 672

Text #1

Max Range: 1.0454. Min Range: -1.0454

Max Act: 1.0330. Min Act: -0.0000

Data Index: 482749 (C4 (Web Text))

Max Activating Token Index: 153

Text #2

Max Range: 1.0454. Min Range: -1.0454

Max Act: 1.0105. Min Act: -0.0000

Data Index: 81673 (C4 (Web Text))

Max Activating Token Index: 120

Text #3

Max Range: 1.0454. Min Range: -1.0454

Max Act: 0.9436. Min Act: -0.0000

Data Index: 1144064 (C4 (Web Text))

Max Activating Token Index: 70

Text #4

Max Range: 1.0454. Min Range: -1.0454

Max Act: 0.9354. Min Act: -0.0000

Data Index: 329883 (C4 (Web Text))

Max Activating Token Index: 578

Text #5

Max Range: 1.0454. Min Range: -1.0454

Max Act: 0.9078. Min Act: -0.0000

Data Index: 815638 (C4 (Web Text))

Max Activating Token Index: 287

Text #6

Max Range: 1.0454. Min Range: -1.0454

Max Act: 0.9183. Min Act: -0.0000

Data Index: 22862 (C4 (Web Text))

Max Activating Token Index: 998

Text #7

Max Range: 1.0454. Min Range: -1.0454

Max Act: 0.9947. Min Act: -0.0000

Data Index: 1059310 (C4 (Web Text))

Max Activating Token Index: 711

Text #8

Max Range: 1.0454. Min Range: -1.0454

Max Act: 0.9447. Min Act: -0.0000

Data Index: 107228 (C4 (Web Text))

Max Activating Token Index: 740

Text #9

Max Range: 1.0454. Min Range: -1.0454

Max Act: 0.8283. Min Act: -0.0000

Data Index: 288967 (C4 (Web Text))

Max Activating Token Index: 112

Text #10

Max Range: 1.0454. Min Range: -1.0454

Max Act: 0.8534. Min Act: -0.0000

Data Index: 470927 (C4 (Web Text))

Max Activating Token Index: 22

Text #11

Max Range: 1.0454. Min Range: -1.0454

Max Act: 0.9741. Min Act: -0.0000

Data Index: 976464 (C4 (Web Text))

Max Activating Token Index: 324

Text #12

Max Range: 1.0454. Min Range: -1.0454

Max Act: 0.8219. Min Act: -0.0000

Data Index: 87067 (C4 (Web Text))

Max Activating Token Index: 734

Text #13

Max Range: 1.0454. Min Range: -1.0454

Max Act: 0.7964. Min Act: -0.0000

Data Index: 643802 (C4 (Web Text))

Max Activating Token Index: 1000

Text #14

Max Range: 1.0454. Min Range: -1.0454

Max Act: 0.8143. Min Act: -0.0000

Data Index: 1071734 (C4 (Web Text))

Max Activating Token Index: 208

Text #15

Max Range: 1.0454. Min Range: -1.0454

Max Act: 0.8818. Min Act: -0.0000

Data Index: 89230 (C4 (Web Text))

Max Activating Token Index: 907

Text #16

Max Range: 1.0454. Min Range: -1.0454

Max Act: 0.7990. Min Act: -0.0000

Data Index: 472695 (C4 (Web Text))

Max Activating Token Index: 113

Text #17

Max Range: 1.0454. Min Range: -1.0454

Max Act: 0.8122. Min Act: -0.0000

Data Index: 393708 (C4 (Web Text))

Max Activating Token Index: 322

Text #18

Max Range: 1.0454. Min Range: -1.0454

Max Act: 0.8071. Min Act: -0.0000

Data Index: 648416 (C4 (Web Text))

Max Activating Token Index: 169

Text #19

Max Range: 1.0454. Min Range: -1.0454

Max Act: 0.7923. Min Act: -0.0000

Data Index: 1239929 (C4 (Web Text))

Max Activating Token Index: 206