Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4856 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0253. Min Act: -0.0002

Data Index: 1529214 (Python Code)

Max Activating Token Index: 398

Text #1

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0166. Min Act: -0.0002

Data Index: 637833 (C4 (Web Text))

Max Activating Token Index: 735

Text #2

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0162. Min Act: -0.0003

Data Index: 1060284 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0142. Min Act: -0.0003

Data Index: 633259 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0147. Min Act: -0.0002

Data Index: 456216 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0131. Min Act: -0.0003

Data Index: 471772 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0101. Min Act: -0.0003

Data Index: 1353764 (C4 (Web Text))

Max Activating Token Index: 979

Text #7

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0126. Min Act: -0.0002

Data Index: 1426822 (Python Code)

Max Activating Token Index: 718

Text #8

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0132. Min Act: -0.0002

Data Index: 1603225 (Python Code)

Max Activating Token Index: 865

Text #9

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0122. Min Act: -0.0002

Data Index: 1500087 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0115. Min Act: -0.0003

Data Index: 641194 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0117. Min Act: -0.0002

Data Index: 1409993 (Python Code)

Max Activating Token Index: 866

Text #12

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0118. Min Act: -0.0002

Data Index: 1499328 (Python Code)

Max Activating Token Index: 884

Text #13

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0117. Min Act: -0.0002

Data Index: 1469154 (Python Code)

Max Activating Token Index: 966

Text #14

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0116. Min Act: -0.0002

Data Index: 972188 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0121. Min Act: -0.0002

Data Index: 784749 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0113. Min Act: -0.0002

Data Index: 1586858 (Python Code)

Max Activating Token Index: 931

Text #17

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0114. Min Act: -0.0002

Data Index: 1622214 (Python Code)

Max Activating Token Index: 603

Text #18

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0117. Min Act: -0.0003

Data Index: 574332 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0101. Min Act: -0.0003

Data Index: 119024 (C4 (Web Text))

Max Activating Token Index: 1023