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

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

Neuron 1745 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: 0.0108. Min Range: -0.0108

Max Act: 0.0107. Min Act: -0.0006

Data Index: 563676 (C4 (Web Text))

Max Activating Token Index: 492

Text #1

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0108. Min Act: -0.0005

Data Index: 1157506 (C4 (Web Text))

Max Activating Token Index: 318

Text #2

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0105. Min Act: -0.0006

Data Index: 1116058 (C4 (Web Text))

Max Activating Token Index: 689

Text #3

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0103. Min Act: -0.0006

Data Index: 137603 (C4 (Web Text))

Max Activating Token Index: 112

Text #4

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0105. Min Act: -0.0006

Data Index: 1129575 (C4 (Web Text))

Max Activating Token Index: 183

Text #5

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0105. Min Act: -0.0006

Data Index: 199751 (C4 (Web Text))

Max Activating Token Index: 849

Text #6

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0102. Min Act: -0.0006

Data Index: 422742 (C4 (Web Text))

Max Activating Token Index: 821

Text #7

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0104. Min Act: -0.0006

Data Index: 1077734 (C4 (Web Text))

Max Activating Token Index: 137

Text #8

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0103. Min Act: -0.0006

Data Index: 1147458 (C4 (Web Text))

Max Activating Token Index: 676

Text #9

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0101. Min Act: -0.0006

Data Index: 119930 (C4 (Web Text))

Max Activating Token Index: 445

Text #10

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0103. Min Act: -0.0006

Data Index: 428507 (C4 (Web Text))

Max Activating Token Index: 719

Text #11

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0100. Min Act: -0.0007

Data Index: 102770 (C4 (Web Text))

Max Activating Token Index: 682

Text #12

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0100. Min Act: -0.0005

Data Index: 1237414 (C4 (Web Text))

Max Activating Token Index: 354

Text #13

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0100. Min Act: -0.0006

Data Index: 190473 (C4 (Web Text))

Max Activating Token Index: 191

Text #14

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0100. Min Act: -0.0006

Data Index: 1085557 (C4 (Web Text))

Max Activating Token Index: 937

Text #15

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0098. Min Act: -0.0006

Data Index: 99223 (C4 (Web Text))

Max Activating Token Index: 90

Text #16

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0097. Min Act: -0.0006

Data Index: 400671 (C4 (Web Text))

Max Activating Token Index: 737

Text #17

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0096. Min Act: -0.0006

Data Index: 137070 (C4 (Web Text))

Max Activating Token Index: 157

Text #18

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0095. Min Act: -0.0006

Data Index: 1049401 (C4 (Web Text))

Max Activating Token Index: 404

Text #19

Max Range: 0.0108. Min Range: -0.0108

Max Act: 0.0095. Min Act: -0.0006

Data Index: 1094383 (C4 (Web Text))

Max Activating Token Index: 512