Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 385 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0132. Min Act: -0.0006

Data Index: 230104 (C4 (Web Text))

Max Activating Token Index: 650

Text #1

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0120. Min Act: -0.0006

Data Index: 489328 (C4 (Web Text))

Max Activating Token Index: 697

Text #2

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0115. Min Act: -0.0006

Data Index: 475937 (C4 (Web Text))

Max Activating Token Index: 422

Text #3

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0116. Min Act: -0.0006

Data Index: 922176 (C4 (Web Text))

Max Activating Token Index: 307

Text #4

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0116. Min Act: -0.0006

Data Index: 92089 (C4 (Web Text))

Max Activating Token Index: 262

Text #5

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0115. Min Act: -0.0006

Data Index: 1074861 (C4 (Web Text))

Max Activating Token Index: 317

Text #6

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0121. Min Act: -0.0006

Data Index: 959814 (C4 (Web Text))

Max Activating Token Index: 298

Text #7

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0110. Min Act: -0.0006

Data Index: 82463 (C4 (Web Text))

Max Activating Token Index: 579

Text #8

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0118. Min Act: -0.0006

Data Index: 660349 (C4 (Web Text))

Max Activating Token Index: 899

Text #9

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0110. Min Act: -0.0006

Data Index: 248675 (C4 (Web Text))

Max Activating Token Index: 528

Text #10

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0113. Min Act: -0.0006

Data Index: 227712 (C4 (Web Text))

Max Activating Token Index: 166

Text #11

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0126. Min Act: -0.0006

Data Index: 1124902 (C4 (Web Text))

Max Activating Token Index: 458

Text #12

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0106. Min Act: -0.0006

Data Index: 1114807 (C4 (Web Text))

Max Activating Token Index: 283

Text #13

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0106. Min Act: -0.0006

Data Index: 162242 (C4 (Web Text))

Max Activating Token Index: 582

Text #14

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0106. Min Act: -0.0006

Data Index: 748049 (C4 (Web Text))

Max Activating Token Index: 494

Text #15

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0111. Min Act: -0.0006

Data Index: 741319 (C4 (Web Text))

Max Activating Token Index: 251

Text #16

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0111. Min Act: -0.0006

Data Index: 959662 (C4 (Web Text))

Max Activating Token Index: 660

Text #17

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0113. Min Act: -0.0006

Data Index: 270937 (C4 (Web Text))

Max Activating Token Index: 145

Text #18

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0099. Min Act: -0.0006

Data Index: 1322428 (C4 (Web Text))

Max Activating Token Index: 448

Text #19

Max Range: 0.0132. Min Range: -0.0132

Max Act: 0.0107. Min Act: -0.0006

Data Index: 270331 (C4 (Web Text))

Max Activating Token Index: 780