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

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

Neuron 1790 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: 0.0107. Min Range: -0.0107

Max Act: 0.0107. Min Act: -0.0002

Data Index: 1150793 (C4 (Web Text))

Max Activating Token Index: 991

Text #1

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0101. Min Act: -0.0002

Data Index: 810545 (C4 (Web Text))

Max Activating Token Index: 264

Text #2

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0099. Min Act: -0.0002

Data Index: 224905 (C4 (Web Text))

Max Activating Token Index: 83

Text #3

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0095. Min Act: -0.0002

Data Index: 52683 (C4 (Web Text))

Max Activating Token Index: 43

Text #4

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0098. Min Act: -0.0002

Data Index: 555965 (C4 (Web Text))

Max Activating Token Index: 495

Text #5

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0097. Min Act: -0.0002

Data Index: 1335340 (C4 (Web Text))

Max Activating Token Index: 369

Text #6

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0095. Min Act: -0.0002

Data Index: 817492 (C4 (Web Text))

Max Activating Token Index: 184

Text #7

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0096. Min Act: -0.0002

Data Index: 940031 (C4 (Web Text))

Max Activating Token Index: 354

Text #8

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0093. Min Act: -0.0002

Data Index: 748328 (C4 (Web Text))

Max Activating Token Index: 131

Text #9

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0093. Min Act: -0.0002

Data Index: 1081593 (C4 (Web Text))

Max Activating Token Index: 601

Text #10

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0095. Min Act: -0.0002

Data Index: 291150 (C4 (Web Text))

Max Activating Token Index: 899

Text #11

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0093. Min Act: -0.0002

Data Index: 340881 (C4 (Web Text))

Max Activating Token Index: 851

Text #12

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0094. Min Act: -0.0002

Data Index: 101661 (C4 (Web Text))

Max Activating Token Index: 434

Text #13

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0092. Min Act: -0.0002

Data Index: 434891 (C4 (Web Text))

Max Activating Token Index: 77

Text #14

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0091. Min Act: -0.0002

Data Index: 575857 (C4 (Web Text))

Max Activating Token Index: 410

Text #15

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0091. Min Act: -0.0002

Data Index: 1191227 (C4 (Web Text))

Max Activating Token Index: 504

Text #16

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0090. Min Act: -0.0002

Data Index: 1086052 (C4 (Web Text))

Max Activating Token Index: 284

Text #17

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0090. Min Act: -0.0002

Data Index: 1108035 (C4 (Web Text))

Max Activating Token Index: 606

Text #18

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0090. Min Act: -0.0002

Data Index: 248348 (C4 (Web Text))

Max Activating Token Index: 289

Text #19

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0090. Min Act: -0.0002

Data Index: 210374 (C4 (Web Text))

Max Activating Token Index: 409