Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 850 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0134. Min Act: -0.0003

Data Index: 811878 (C4 (Web Text))

Max Activating Token Index: 228

Text #1

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0135. Min Act: -0.0003

Data Index: 760786 (C4 (Web Text))

Max Activating Token Index: 291

Text #2

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0121. Min Act: -0.0003

Data Index: 779917 (C4 (Web Text))

Max Activating Token Index: 548

Text #3

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0136. Min Act: -0.0003

Data Index: 748988 (C4 (Web Text))

Max Activating Token Index: 97

Text #4

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0107. Min Act: -0.0003

Data Index: 1416898 (Python Code)

Max Activating Token Index: 562

Text #5

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0131. Min Act: -0.0004

Data Index: 736689 (C4 (Web Text))

Max Activating Token Index: 631

Text #6

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0105. Min Act: -0.0003

Data Index: 1466770 (Python Code)

Max Activating Token Index: 551

Text #7

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0119. Min Act: -0.0003

Data Index: 1291771 (C4 (Web Text))

Max Activating Token Index: 185

Text #8

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0119. Min Act: -0.0003

Data Index: 174115 (C4 (Web Text))

Max Activating Token Index: 502

Text #9

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0111. Min Act: -0.0003

Data Index: 1604417 (Python Code)

Max Activating Token Index: 741

Text #10

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0116. Min Act: -0.0003

Data Index: 1431094 (Python Code)

Max Activating Token Index: 709

Text #11

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0115. Min Act: -0.0003

Data Index: 1496073 (Python Code)

Max Activating Token Index: 819

Text #12

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0110. Min Act: -0.0003

Data Index: 1636886 (Python Code)

Max Activating Token Index: 514

Text #13

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0108. Min Act: -0.0003

Data Index: 60940 (C4 (Web Text))

Max Activating Token Index: 380

Text #14

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0113. Min Act: -0.0003

Data Index: 1565841 (Python Code)

Max Activating Token Index: 442

Text #15

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0106. Min Act: -0.0003

Data Index: 1545996 (Python Code)

Max Activating Token Index: 300

Text #16

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0101. Min Act: -0.0003

Data Index: 716378 (C4 (Web Text))

Max Activating Token Index: 659

Text #17

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0117. Min Act: -0.0003

Data Index: 1645909 (Python Code)

Max Activating Token Index: 556

Text #18

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0115. Min Act: -0.0003

Data Index: 1626800 (Python Code)

Max Activating Token Index: 76

Text #19

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0110. Min Act: -0.0003

Data Index: 12992 (C4 (Web Text))

Max Activating Token Index: 979