Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 3034 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0131. Min Act: -0.0004

Data Index: 318609 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0130. Min Act: -0.0004

Data Index: 1173603 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0129. Min Act: -0.0004

Data Index: 411136 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0128. Min Act: -0.0003

Data Index: 1530329 (Python Code)

Max Activating Token Index: 84

Text #4

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0122. Min Act: -0.0004

Data Index: 424392 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0124. Min Act: -0.0003

Data Index: 1502098 (Python Code)

Max Activating Token Index: 765

Text #6

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0120. Min Act: -0.0004

Data Index: 15077 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0122. Min Act: -0.0003

Data Index: 1270175 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0120. Min Act: -0.0003

Data Index: 1522797 (Python Code)

Max Activating Token Index: 247

Text #9

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0120. Min Act: -0.0003

Data Index: 466932 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0120. Min Act: -0.0003

Data Index: 1489516 (Python Code)

Max Activating Token Index: 627

Text #11

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0117. Min Act: -0.0003

Data Index: 1460110 (Python Code)

Max Activating Token Index: 220

Text #12

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0120. Min Act: -0.0004

Data Index: 62184 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0118. Min Act: -0.0004

Data Index: 905547 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0119. Min Act: -0.0003

Data Index: 1406345 (Python Code)

Max Activating Token Index: 81

Text #15

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0121. Min Act: -0.0004

Data Index: 1297790 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0121. Min Act: -0.0003

Data Index: 767020 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0119. Min Act: -0.0004

Data Index: 1109963 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0119. Min Act: -0.0003

Data Index: 120749 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0131. Min Range: -0.0131

Max Act: 0.0118. Min Act: -0.0003

Data Index: 1420825 (Python Code)

Max Activating Token Index: 111