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

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

Neuron 4788 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0172. Min Act: -0.0002

Data Index: 1516111 (Python Code)

Max Activating Token Index: 290

Text #1

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0116. Min Act: -0.0002

Data Index: 554155 (C4 (Web Text))

Max Activating Token Index: 279

Text #2

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0128. Min Act: -0.0002

Data Index: 415808 (C4 (Web Text))

Max Activating Token Index: 702

Text #3

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0111. Min Act: -0.0002

Data Index: 1359360 (C4 (Web Text))

Max Activating Token Index: 189

Text #4

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0127. Min Act: -0.0002

Data Index: 313597 (C4 (Web Text))

Max Activating Token Index: 414

Text #5

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0129. Min Act: -0.0002

Data Index: 1508352 (Python Code)

Max Activating Token Index: 23

Text #6

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0106. Min Act: -0.0002

Data Index: 162098 (C4 (Web Text))

Max Activating Token Index: 707

Text #7

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0132. Min Act: -0.0002

Data Index: 144116 (C4 (Web Text))

Max Activating Token Index: 840

Text #8

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0127. Min Act: -0.0002

Data Index: 651896 (C4 (Web Text))

Max Activating Token Index: 776

Text #9

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0122. Min Act: -0.0002

Data Index: 674379 (C4 (Web Text))

Max Activating Token Index: 26

Text #10

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0114. Min Act: -0.0002

Data Index: 92718 (C4 (Web Text))

Max Activating Token Index: 199

Text #11

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0093. Min Act: -0.0002

Data Index: 123136 (C4 (Web Text))

Max Activating Token Index: 319

Text #12

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0120. Min Act: -0.0002

Data Index: 794329 (C4 (Web Text))

Max Activating Token Index: 501

Text #13

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0115. Min Act: -0.0002

Data Index: 319648 (C4 (Web Text))

Max Activating Token Index: 47

Text #14

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0107. Min Act: -0.0002

Data Index: 229648 (C4 (Web Text))

Max Activating Token Index: 582

Text #15

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0107. Min Act: -0.0002

Data Index: 557402 (C4 (Web Text))

Max Activating Token Index: 797

Text #16

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0118. Min Act: -0.0002

Data Index: 88165 (C4 (Web Text))

Max Activating Token Index: 675

Text #17

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0123. Min Act: -0.0002

Data Index: 1318670 (C4 (Web Text))

Max Activating Token Index: 597

Text #18

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0117. Min Act: -0.0002

Data Index: 514745 (C4 (Web Text))

Max Activating Token Index: 373

Text #19

Max Range: 0.0172. Min Range: -0.0172

Max Act: 0.0117. Min Act: -0.0002

Data Index: 23671 (C4 (Web Text))

Max Activating Token Index: 365