Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1548 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0075. Min Act: -0.0006

Data Index: 1036474 (C4 (Web Text))

Max Activating Token Index: 1009

Text #1

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0071. Min Act: -0.0006

Data Index: 573121 (C4 (Web Text))

Max Activating Token Index: 60

Text #2

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0067. Min Act: -0.0007

Data Index: 368250 (C4 (Web Text))

Max Activating Token Index: 894

Text #3

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0065. Min Act: -0.0006

Data Index: 883461 (C4 (Web Text))

Max Activating Token Index: 950

Text #4

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0067. Min Act: -0.0006

Data Index: 556710 (C4 (Web Text))

Max Activating Token Index: 192

Text #5

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0062. Min Act: -0.0006

Data Index: 276707 (C4 (Web Text))

Max Activating Token Index: 256

Text #6

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0062. Min Act: -0.0006

Data Index: 1297269 (C4 (Web Text))

Max Activating Token Index: 4

Text #7

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0063. Min Act: -0.0006

Data Index: 312878 (C4 (Web Text))

Max Activating Token Index: 158

Text #8

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0063. Min Act: -0.0006

Data Index: 364339 (C4 (Web Text))

Max Activating Token Index: 140

Text #9

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0063. Min Act: -0.0006

Data Index: 1016842 (C4 (Web Text))

Max Activating Token Index: 853

Text #10

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0063. Min Act: -0.0006

Data Index: 1023188 (C4 (Web Text))

Max Activating Token Index: 568

Text #11

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0063. Min Act: -0.0006

Data Index: 391089 (C4 (Web Text))

Max Activating Token Index: 374

Text #12

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0061. Min Act: -0.0006

Data Index: 192299 (C4 (Web Text))

Max Activating Token Index: 854

Text #13

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0060. Min Act: -0.0006

Data Index: 103170 (C4 (Web Text))

Max Activating Token Index: 9

Text #14

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0059. Min Act: -0.0006

Data Index: 81837 (C4 (Web Text))

Max Activating Token Index: 23

Text #15

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0059. Min Act: -0.0006

Data Index: 873402 (C4 (Web Text))

Max Activating Token Index: 249

Text #16

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0059. Min Act: -0.0006

Data Index: 762461 (C4 (Web Text))

Max Activating Token Index: 298

Text #17

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0059. Min Act: -0.0006

Data Index: 1247306 (C4 (Web Text))

Max Activating Token Index: 389

Text #18

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0059. Min Act: -0.0006

Data Index: 351478 (C4 (Web Text))

Max Activating Token Index: 570

Text #19

Max Range: 0.0075. Min Range: -0.0075

Max Act: 0.0059. Min Act: -0.0006

Data Index: 255367 (C4 (Web Text))

Max Activating Token Index: 961