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

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

Neuron 678 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: 0.0218. Min Range: -0.0218

Max Act: 0.0218. Min Act: -0.0003

Data Index: 1001964 (C4 (Web Text))

Max Activating Token Index: 971

Text #1

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0141. Min Act: -0.0003

Data Index: 716108 (C4 (Web Text))

Max Activating Token Index: 951

Text #2

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0133. Min Act: -0.0004

Data Index: 285738 (C4 (Web Text))

Max Activating Token Index: 976

Text #3

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0136. Min Act: -0.0003

Data Index: 118499 (C4 (Web Text))

Max Activating Token Index: 468

Text #4

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0129. Min Act: -0.0003

Data Index: 623434 (C4 (Web Text))

Max Activating Token Index: 288

Text #5

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0132. Min Act: -0.0003

Data Index: 1307001 (C4 (Web Text))

Max Activating Token Index: 996

Text #6

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0130. Min Act: -0.0004

Data Index: 987403 (C4 (Web Text))

Max Activating Token Index: 512

Text #7

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0129. Min Act: -0.0003

Data Index: 62985 (C4 (Web Text))

Max Activating Token Index: 838

Text #8

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0127. Min Act: -0.0003

Data Index: 24496 (C4 (Web Text))

Max Activating Token Index: 369

Text #9

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0122. Min Act: -0.0004

Data Index: 326829 (C4 (Web Text))

Max Activating Token Index: 770

Text #10

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0127. Min Act: -0.0003

Data Index: 179178 (C4 (Web Text))

Max Activating Token Index: 423

Text #11

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0117. Min Act: -0.0003

Data Index: 1313135 (C4 (Web Text))

Max Activating Token Index: 298

Text #12

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0120. Min Act: -0.0003

Data Index: 833583 (C4 (Web Text))

Max Activating Token Index: 16

Text #13

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0120. Min Act: -0.0003

Data Index: 468503 (C4 (Web Text))

Max Activating Token Index: 375

Text #14

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0122. Min Act: -0.0003

Data Index: 935641 (C4 (Web Text))

Max Activating Token Index: 1016

Text #15

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0124. Min Act: -0.0003

Data Index: 1140012 (C4 (Web Text))

Max Activating Token Index: 457

Text #16

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0118. Min Act: -0.0003

Data Index: 96196 (C4 (Web Text))

Max Activating Token Index: 199

Text #17

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0121. Min Act: -0.0003

Data Index: 571741 (C4 (Web Text))

Max Activating Token Index: 483

Text #18

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0115. Min Act: -0.0003

Data Index: 685537 (C4 (Web Text))

Max Activating Token Index: 988

Text #19

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0114. Min Act: -0.0003

Data Index: 1161663 (C4 (Web Text))

Max Activating Token Index: 534