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

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

Neuron 529 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: 0.0110. Min Range: -0.0110

Max Act: 0.0108. Min Act: -0.0006

Data Index: 167439 (C4 (Web Text))

Max Activating Token Index: 941

Text #1

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0110. Min Act: -0.0006

Data Index: 314838 (C4 (Web Text))

Max Activating Token Index: 919

Text #2

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0105. Min Act: -0.0006

Data Index: 1234553 (C4 (Web Text))

Max Activating Token Index: 940

Text #3

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0106. Min Act: -0.0006

Data Index: 1134407 (C4 (Web Text))

Max Activating Token Index: 935

Text #4

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0107. Min Act: -0.0006

Data Index: 1282492 (C4 (Web Text))

Max Activating Token Index: 249

Text #5

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0103. Min Act: -0.0006

Data Index: 1084145 (C4 (Web Text))

Max Activating Token Index: 831

Text #6

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0104. Min Act: -0.0006

Data Index: 197331 (C4 (Web Text))

Max Activating Token Index: 952

Text #7

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0104. Min Act: -0.0006

Data Index: 455127 (C4 (Web Text))

Max Activating Token Index: 244

Text #8

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0103. Min Act: -0.0006

Data Index: 1320958 (C4 (Web Text))

Max Activating Token Index: 921

Text #9

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0101. Min Act: -0.0006

Data Index: 754673 (C4 (Web Text))

Max Activating Token Index: 826

Text #10

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0104. Min Act: -0.0006

Data Index: 213186 (C4 (Web Text))

Max Activating Token Index: 509

Text #11

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0099. Min Act: -0.0006

Data Index: 1307806 (C4 (Web Text))

Max Activating Token Index: 1012

Text #12

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0104. Min Act: -0.0006

Data Index: 687723 (C4 (Web Text))

Max Activating Token Index: 712

Text #13

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0101. Min Act: -0.0007

Data Index: 833840 (C4 (Web Text))

Max Activating Token Index: 630

Text #14

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0100. Min Act: -0.0006

Data Index: 738607 (C4 (Web Text))

Max Activating Token Index: 509

Text #15

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0097. Min Act: -0.0006

Data Index: 1203357 (C4 (Web Text))

Max Activating Token Index: 687

Text #16

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0099. Min Act: -0.0006

Data Index: 1071978 (C4 (Web Text))

Max Activating Token Index: 943

Text #17

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0097. Min Act: -0.0006

Data Index: 250952 (C4 (Web Text))

Max Activating Token Index: 833

Text #18

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0096. Min Act: -0.0006

Data Index: 116928 (C4 (Web Text))

Max Activating Token Index: 519

Text #19

Max Range: 0.0110. Min Range: -0.0110

Max Act: 0.0101. Min Act: -0.0006

Data Index: 1139585 (C4 (Web Text))

Max Activating Token Index: 711