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

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

Neuron 3596 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0080. Min Range: -0.0080

Max Act: 0.0080. Min Act: -0.0002

Data Index: 223768 (C4 (Web Text))

Max Activating Token Index: 314

Text #1

Max Range: 0.0080. Min Range: -0.0080

Max Act: 0.0078. Min Act: -0.0002

Data Index: 493197 (C4 (Web Text))

Max Activating Token Index: 228

Text #2

Max Range: 0.0080. Min Range: -0.0080

Max Act: 0.0074. Min Act: -0.0002

Data Index: 353722 (C4 (Web Text))

Max Activating Token Index: 394

Text #3

Max Range: 0.0080. Min Range: -0.0080

Max Act: 0.0073. Min Act: -0.0002

Data Index: 16788 (C4 (Web Text))

Max Activating Token Index: 254

Text #4

Max Range: 0.0080. Min Range: -0.0080

Max Act: 0.0073. Min Act: -0.0002

Data Index: 10664 (C4 (Web Text))

Max Activating Token Index: 370

Text #5

Max Range: 0.0080. Min Range: -0.0080

Max Act: 0.0071. Min Act: -0.0002

Data Index: 391627 (C4 (Web Text))

Max Activating Token Index: 203

Text #6

Max Range: 0.0080. Min Range: -0.0080

Max Act: 0.0070. Min Act: -0.0002

Data Index: 1084728 (C4 (Web Text))

Max Activating Token Index: 906

Text #7

Max Range: 0.0080. Min Range: -0.0080

Max Act: 0.0069. Min Act: -0.0002

Data Index: 1187827 (C4 (Web Text))

Max Activating Token Index: 669

Text #8

Max Range: 0.0080. Min Range: -0.0080

Max Act: 0.0068. Min Act: -0.0002

Data Index: 1020432 (C4 (Web Text))

Max Activating Token Index: 33

Text #9

Max Range: 0.0080. Min Range: -0.0080

Max Act: 0.0069. Min Act: -0.0002

Data Index: 926970 (C4 (Web Text))

Max Activating Token Index: 805

Text #10

Max Range: 0.0080. Min Range: -0.0080

Max Act: 0.0069. Min Act: -0.0002

Data Index: 961849 (C4 (Web Text))

Max Activating Token Index: 89

Text #11

Max Range: 0.0080. Min Range: -0.0080

Max Act: 0.0068. Min Act: -0.0002

Data Index: 569313 (C4 (Web Text))

Max Activating Token Index: 20

Text #12

Max Range: 0.0080. Min Range: -0.0080

Max Act: 0.0068. Min Act: -0.0002

Data Index: 370614 (C4 (Web Text))

Max Activating Token Index: 24

Text #13

Max Range: 0.0080. Min Range: -0.0080

Max Act: 0.0068. Min Act: -0.0002

Data Index: 1093619 (C4 (Web Text))

Max Activating Token Index: 409

Text #14

Max Range: 0.0080. Min Range: -0.0080

Max Act: 0.0068. Min Act: -0.0002

Data Index: 1128765 (C4 (Web Text))

Max Activating Token Index: 470

Text #15

Max Range: 0.0080. Min Range: -0.0080

Max Act: 0.0068. Min Act: -0.0002

Data Index: 1323702 (C4 (Web Text))

Max Activating Token Index: 138

Text #16

Max Range: 0.0080. Min Range: -0.0080

Max Act: 0.0068. Min Act: -0.0002

Data Index: 422096 (C4 (Web Text))

Max Activating Token Index: 59

Text #17

Max Range: 0.0080. Min Range: -0.0080

Max Act: 0.0068. Min Act: -0.0002

Data Index: 1165682 (C4 (Web Text))

Max Activating Token Index: 487

Text #18

Max Range: 0.0080. Min Range: -0.0080

Max Act: 0.0067. Min Act: -0.0002

Data Index: 1118044 (C4 (Web Text))

Max Activating Token Index: 834

Text #19

Max Range: 0.0080. Min Range: -0.0080

Max Act: 0.0067. Min Act: -0.0002

Data Index: 93856 (C4 (Web Text))

Max Activating Token Index: 1020