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

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

Neuron 209 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: 0.0107. Min Range: -0.0107

Max Act: 0.0107. Min Act: -0.0006

Data Index: 884906 (C4 (Web Text))

Max Activating Token Index: 30

Text #1

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0105. Min Act: -0.0006

Data Index: 1063173 (C4 (Web Text))

Max Activating Token Index: 514

Text #2

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0097. Min Act: -0.0006

Data Index: 74473 (C4 (Web Text))

Max Activating Token Index: 343

Text #3

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0103. Min Act: -0.0006

Data Index: 19260 (C4 (Web Text))

Max Activating Token Index: 888

Text #4

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0099. Min Act: -0.0006

Data Index: 1122877 (C4 (Web Text))

Max Activating Token Index: 782

Text #5

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0096. Min Act: -0.0006

Data Index: 914713 (C4 (Web Text))

Max Activating Token Index: 748

Text #6

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0093. Min Act: -0.0006

Data Index: 1015182 (C4 (Web Text))

Max Activating Token Index: 310

Text #7

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0091. Min Act: -0.0006

Data Index: 764785 (C4 (Web Text))

Max Activating Token Index: 598

Text #8

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0094. Min Act: -0.0006

Data Index: 705540 (C4 (Web Text))

Max Activating Token Index: 89

Text #9

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0091. Min Act: -0.0006

Data Index: 665216 (C4 (Web Text))

Max Activating Token Index: 558

Text #10

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0093. Min Act: -0.0006

Data Index: 65058 (C4 (Web Text))

Max Activating Token Index: 756

Text #11

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0094. Min Act: -0.0006

Data Index: 891203 (C4 (Web Text))

Max Activating Token Index: 312

Text #12

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0090. Min Act: -0.0006

Data Index: 1202024 (C4 (Web Text))

Max Activating Token Index: 774

Text #13

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0093. Min Act: -0.0006

Data Index: 273095 (C4 (Web Text))

Max Activating Token Index: 800

Text #14

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0090. Min Act: -0.0006

Data Index: 299013 (C4 (Web Text))

Max Activating Token Index: 896

Text #15

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0089. Min Act: -0.0006

Data Index: 570315 (C4 (Web Text))

Max Activating Token Index: 86

Text #16

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0085. Min Act: -0.0006

Data Index: 230346 (C4 (Web Text))

Max Activating Token Index: 725

Text #17

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0091. Min Act: -0.0006

Data Index: 125352 (C4 (Web Text))

Max Activating Token Index: 12

Text #18

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0086. Min Act: -0.0006

Data Index: 442142 (C4 (Web Text))

Max Activating Token Index: 732

Text #19

Max Range: 0.0107. Min Range: -0.0107

Max Act: 0.0086. Min Act: -0.0006

Data Index: 174966 (C4 (Web Text))

Max Activating Token Index: 582