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

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

Neuron 4212 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0135. Min Act: -0.0002

Data Index: 1311773 (C4 (Web Text))

Max Activating Token Index: 39

Text #1

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0125. Min Act: -0.0002

Data Index: 339386 (C4 (Web Text))

Max Activating Token Index: 234

Text #2

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0124. Min Act: -0.0002

Data Index: 12765 (C4 (Web Text))

Max Activating Token Index: 270

Text #3

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0122. Min Act: -0.0002

Data Index: 289521 (C4 (Web Text))

Max Activating Token Index: 310

Text #4

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0120. Min Act: -0.0002

Data Index: 1195526 (C4 (Web Text))

Max Activating Token Index: 897

Text #5

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0118. Min Act: -0.0002

Data Index: 623698 (C4 (Web Text))

Max Activating Token Index: 317

Text #6

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0120. Min Act: -0.0002

Data Index: 23617 (C4 (Web Text))

Max Activating Token Index: 725

Text #7

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0116. Min Act: -0.0002

Data Index: 814021 (C4 (Web Text))

Max Activating Token Index: 853

Text #8

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0116. Min Act: -0.0002

Data Index: 670655 (C4 (Web Text))

Max Activating Token Index: 169

Text #9

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0115. Min Act: -0.0002

Data Index: 16683 (C4 (Web Text))

Max Activating Token Index: 945

Text #10

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0115. Min Act: -0.0002

Data Index: 958412 (C4 (Web Text))

Max Activating Token Index: 548

Text #11

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0115. Min Act: -0.0002

Data Index: 856915 (C4 (Web Text))

Max Activating Token Index: 922

Text #12

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0112. Min Act: -0.0002

Data Index: 495786 (C4 (Web Text))

Max Activating Token Index: 551

Text #13

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0113. Min Act: -0.0002

Data Index: 526000 (C4 (Web Text))

Max Activating Token Index: 416

Text #14

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0113. Min Act: -0.0002

Data Index: 810343 (C4 (Web Text))

Max Activating Token Index: 661

Text #15

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0113. Min Act: -0.0002

Data Index: 1327598 (C4 (Web Text))

Max Activating Token Index: 595

Text #16

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0113. Min Act: -0.0002

Data Index: 542337 (C4 (Web Text))

Max Activating Token Index: 558

Text #17

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0112. Min Act: -0.0002

Data Index: 424136 (C4 (Web Text))

Max Activating Token Index: 585

Text #18

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0112. Min Act: -0.0002

Data Index: 343595 (C4 (Web Text))

Max Activating Token Index: 219

Text #19

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0112. Min Act: -0.0002

Data Index: 665442 (C4 (Web Text))

Max Activating Token Index: 383