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

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

Neuron 2513 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: 0.0079. Min Range: -0.0079

Max Act: 0.0079. Min Act: -0.0003

Data Index: 868801 (C4 (Web Text))

Max Activating Token Index: 12

Text #1

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0079. Min Act: -0.0003

Data Index: 1309465 (C4 (Web Text))

Max Activating Token Index: 9

Text #2

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0072. Min Act: -0.0002

Data Index: 28244 (C4 (Web Text))

Max Activating Token Index: 143

Text #3

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0071. Min Act: -0.0003

Data Index: 436209 (C4 (Web Text))

Max Activating Token Index: 702

Text #4

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0068. Min Act: -0.0003

Data Index: 86139 (C4 (Web Text))

Max Activating Token Index: 418

Text #5

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0069. Min Act: -0.0003

Data Index: 1126901 (C4 (Web Text))

Max Activating Token Index: 18

Text #6

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0067. Min Act: -0.0003

Data Index: 369548 (C4 (Web Text))

Max Activating Token Index: 885

Text #7

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0067. Min Act: -0.0003

Data Index: 519843 (C4 (Web Text))

Max Activating Token Index: 509

Text #8

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0068. Min Act: -0.0003

Data Index: 265044 (C4 (Web Text))

Max Activating Token Index: 961

Text #9

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0066. Min Act: -0.0003

Data Index: 1088876 (C4 (Web Text))

Max Activating Token Index: 652

Text #10

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0065. Min Act: -0.0003

Data Index: 684894 (C4 (Web Text))

Max Activating Token Index: 507

Text #11

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0065. Min Act: -0.0003

Data Index: 357156 (C4 (Web Text))

Max Activating Token Index: 225

Text #12

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0064. Min Act: -0.0003

Data Index: 1074573 (C4 (Web Text))

Max Activating Token Index: 645

Text #13

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0064. Min Act: -0.0002

Data Index: 1077709 (C4 (Web Text))

Max Activating Token Index: 324

Text #14

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0064. Min Act: -0.0003

Data Index: 848319 (C4 (Web Text))

Max Activating Token Index: 301

Text #15

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0063. Min Act: -0.0002

Data Index: 149971 (C4 (Web Text))

Max Activating Token Index: 548

Text #16

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0062. Min Act: -0.0003

Data Index: 381981 (C4 (Web Text))

Max Activating Token Index: 103

Text #17

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0062. Min Act: -0.0003

Data Index: 204721 (C4 (Web Text))

Max Activating Token Index: 134

Text #18

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0062. Min Act: -0.0002

Data Index: 360881 (C4 (Web Text))

Max Activating Token Index: 793

Text #19

Max Range: 0.0079. Min Range: -0.0079

Max Act: 0.0062. Min Act: -0.0002

Data Index: 611688 (C4 (Web Text))

Max Activating Token Index: 12