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

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

Neuron 1177 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: 0.0107. Min Range: -0.0107

Max Act: 0.0107. Min Act: -0.0006

Data Index: 181912 (C4 (Web Text))

Max Activating Token Index: 649

Text #1

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0103. Min Act: -0.0006

Data Index: 1325715 (C4 (Web Text))

Max Activating Token Index: 513

Text #2

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0101. Min Act: -0.0006

Data Index: 627638 (C4 (Web Text))

Max Activating Token Index: 913

Text #3

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0099. Min Act: -0.0006

Data Index: 1029258 (C4 (Web Text))

Max Activating Token Index: 1018

Text #4

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0096. Min Act: -0.0006

Data Index: 693447 (C4 (Web Text))

Max Activating Token Index: 226

Text #5

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0097. Min Act: -0.0006

Data Index: 569681 (C4 (Web Text))

Max Activating Token Index: 159

Text #6

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0096. Min Act: -0.0006

Data Index: 618401 (C4 (Web Text))

Max Activating Token Index: 678

Text #7

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0093. Min Act: -0.0006

Data Index: 660660 (C4 (Web Text))

Max Activating Token Index: 420

Text #8

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0091. Min Act: -0.0006

Data Index: 752494 (C4 (Web Text))

Max Activating Token Index: 711

Text #9

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0094. Min Act: -0.0006

Data Index: 1136242 (C4 (Web Text))

Max Activating Token Index: 481

Text #10

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0089. Min Act: -0.0006

Data Index: 805243 (C4 (Web Text))

Max Activating Token Index: 55

Text #11

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0088. Min Act: -0.0007

Data Index: 512869 (C4 (Web Text))

Max Activating Token Index: 915

Text #12

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0088. Min Act: -0.0006

Data Index: 351349 (C4 (Web Text))

Max Activating Token Index: 272

Text #13

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0090. Min Act: -0.0006

Data Index: 1295262 (C4 (Web Text))

Max Activating Token Index: 111

Text #14

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0090. Min Act: -0.0006

Data Index: 241803 (C4 (Web Text))

Max Activating Token Index: 433

Text #15

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0087. Min Act: -0.0006

Data Index: 520590 (C4 (Web Text))

Max Activating Token Index: 934

Text #16

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0088. Min Act: -0.0006

Data Index: 533158 (C4 (Web Text))

Max Activating Token Index: 116

Text #17

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0086. Min Act: -0.0006

Data Index: 172557 (C4 (Web Text))

Max Activating Token Index: 899

Text #18

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0085. Min Act: -0.0006

Data Index: 150048 (C4 (Web Text))

Max Activating Token Index: 741

Text #19

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0084. Min Act: -0.0006

Data Index: 474997 (C4 (Web Text))

Max Activating Token Index: 277