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

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

Neuron 1031 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: 0.0128. Min Range: -0.0128

Max Act: 0.0128. Min Act: -0.0006

Data Index: 99942 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0128. Min Range: -0.0128

Max Act: 0.0121. Min Act: -0.0005

Data Index: 395871 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0128. Min Range: -0.0128

Max Act: 0.0114. Min Act: -0.0006

Data Index: 377800 (C4 (Web Text))

Max Activating Token Index: 899

Text #3

Max Range: 0.0128. Min Range: -0.0128

Max Act: 0.0112. Min Act: -0.0006

Data Index: 1027903 (C4 (Web Text))

Max Activating Token Index: 47

Text #4

Max Range: 0.0128. Min Range: -0.0128

Max Act: 0.0106. Min Act: -0.0006

Data Index: 531547 (C4 (Web Text))

Max Activating Token Index: 802

Text #5

Max Range: 0.0128. Min Range: -0.0128

Max Act: 0.0104. Min Act: -0.0006

Data Index: 573245 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0128. Min Range: -0.0128

Max Act: 0.0097. Min Act: -0.0006

Data Index: 175046 (C4 (Web Text))

Max Activating Token Index: 9

Text #7

Max Range: 0.0128. Min Range: -0.0128

Max Act: 0.0103. Min Act: -0.0006

Data Index: 838120 (C4 (Web Text))

Max Activating Token Index: 827

Text #8

Max Range: 0.0128. Min Range: -0.0128

Max Act: 0.0100. Min Act: -0.0005

Data Index: 724924 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0128. Min Range: -0.0128

Max Act: 0.0093. Min Act: -0.0005

Data Index: 1413896 (Python Code)

Max Activating Token Index: 892

Text #10

Max Range: 0.0128. Min Range: -0.0128

Max Act: 0.0096. Min Act: -0.0006

Data Index: 1270337 (C4 (Web Text))

Max Activating Token Index: 601

Text #11

Max Range: 0.0128. Min Range: -0.0128

Max Act: 0.0091. Min Act: -0.0006

Data Index: 692313 (C4 (Web Text))

Max Activating Token Index: 839

Text #12

Max Range: 0.0128. Min Range: -0.0128

Max Act: 0.0089. Min Act: -0.0006

Data Index: 357083 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0128. Min Range: -0.0128

Max Act: 0.0087. Min Act: -0.0005

Data Index: 1491968 (Python Code)

Max Activating Token Index: 964

Text #14

Max Range: 0.0128. Min Range: -0.0128

Max Act: 0.0084. Min Act: -0.0006

Data Index: 1588660 (Python Code)

Max Activating Token Index: 686

Text #15

Max Range: 0.0128. Min Range: -0.0128

Max Act: 0.0085. Min Act: -0.0006

Data Index: 1455223 (Python Code)

Max Activating Token Index: 644

Text #16

Max Range: 0.0128. Min Range: -0.0128

Max Act: 0.0087. Min Act: -0.0005

Data Index: 1516884 (Python Code)

Max Activating Token Index: 857

Text #17

Max Range: 0.0128. Min Range: -0.0128

Max Act: 0.0087. Min Act: -0.0005

Data Index: 1362366 (Python Code)

Max Activating Token Index: 106

Text #18

Max Range: 0.0128. Min Range: -0.0128

Max Act: 0.0086. Min Act: -0.0006

Data Index: 1400474 (Python Code)

Max Activating Token Index: 896

Text #19

Max Range: 0.0128. Min Range: -0.0128

Max Act: 0.0085. Min Act: -0.0005

Data Index: 1431942 (Python Code)

Max Activating Token Index: 611