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

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

Neuron 1680 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0108. Min Act: -0.0006

Data Index: 629735 (C4 (Web Text))

Max Activating Token Index: 413

Text #1

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0106. Min Act: -0.0006

Data Index: 461459 (C4 (Web Text))

Max Activating Token Index: 548

Text #2

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0105. Min Act: -0.0006

Data Index: 330294 (C4 (Web Text))

Max Activating Token Index: 240

Text #3

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0105. Min Act: -0.0006

Data Index: 1269563 (C4 (Web Text))

Max Activating Token Index: 738

Text #4

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0104. Min Act: -0.0006

Data Index: 1109421 (C4 (Web Text))

Max Activating Token Index: 81

Text #5

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0104. Min Act: -0.0006

Data Index: 503378 (C4 (Web Text))

Max Activating Token Index: 309

Text #6

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0098. Min Act: -0.0006

Data Index: 909823 (C4 (Web Text))

Max Activating Token Index: 655

Text #7

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0102. Min Act: -0.0006

Data Index: 923001 (C4 (Web Text))

Max Activating Token Index: 392

Text #8

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0102. Min Act: -0.0006

Data Index: 1318164 (C4 (Web Text))

Max Activating Token Index: 144

Text #9

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0101. Min Act: -0.0006

Data Index: 1087073 (C4 (Web Text))

Max Activating Token Index: 118

Text #10

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0103. Min Act: -0.0006

Data Index: 293885 (C4 (Web Text))

Max Activating Token Index: 130

Text #11

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0096. Min Act: -0.0006

Data Index: 247950 (C4 (Web Text))

Max Activating Token Index: 337

Text #12

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0098. Min Act: -0.0006

Data Index: 96881 (C4 (Web Text))

Max Activating Token Index: 716

Text #13

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0098. Min Act: -0.0006

Data Index: 833276 (C4 (Web Text))

Max Activating Token Index: 431

Text #14

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0100. Min Act: -0.0006

Data Index: 1082291 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0097. Min Act: -0.0006

Data Index: 1083951 (C4 (Web Text))

Max Activating Token Index: 179

Text #16

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0092. Min Act: -0.0006

Data Index: 762589 (C4 (Web Text))

Max Activating Token Index: 1007

Text #17

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0098. Min Act: -0.0006

Data Index: 1417123 (Python Code)

Max Activating Token Index: 85

Text #18

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0093. Min Act: -0.0006

Data Index: 1044447 (C4 (Web Text))

Max Activating Token Index: 154

Text #19

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0096. Min Act: -0.0006

Data Index: 451261 (C4 (Web Text))

Max Activating Token Index: 1007