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

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

Neuron 258 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: 0.0149. Min Range: -0.0149

Max Act: 0.0149. Min Act: -0.0006

Data Index: 1208499 (C4 (Web Text))

Max Activating Token Index: 268

Text #1

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0133. Min Act: -0.0006

Data Index: 585746 (C4 (Web Text))

Max Activating Token Index: 928

Text #2

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0139. Min Act: -0.0006

Data Index: 1229638 (C4 (Web Text))

Max Activating Token Index: 1000

Text #3

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0136. Min Act: -0.0006

Data Index: 448161 (C4 (Web Text))

Max Activating Token Index: 852

Text #4

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0126. Min Act: -0.0006

Data Index: 325834 (C4 (Web Text))

Max Activating Token Index: 945

Text #5

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0127. Min Act: -0.0006

Data Index: 629265 (C4 (Web Text))

Max Activating Token Index: 848

Text #6

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0112. Min Act: -0.0006

Data Index: 53461 (C4 (Web Text))

Max Activating Token Index: 870

Text #7

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0120. Min Act: -0.0006

Data Index: 325668 (C4 (Web Text))

Max Activating Token Index: 865

Text #8

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0120. Min Act: -0.0006

Data Index: 873060 (C4 (Web Text))

Max Activating Token Index: 709

Text #9

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0120. Min Act: -0.0006

Data Index: 250983 (C4 (Web Text))

Max Activating Token Index: 595

Text #10

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0113. Min Act: -0.0006

Data Index: 312139 (C4 (Web Text))

Max Activating Token Index: 276

Text #11

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0116. Min Act: -0.0006

Data Index: 1259482 (C4 (Web Text))

Max Activating Token Index: 408

Text #12

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0116. Min Act: -0.0006

Data Index: 300025 (C4 (Web Text))

Max Activating Token Index: 398

Text #13

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0118. Min Act: -0.0006

Data Index: 838425 (C4 (Web Text))

Max Activating Token Index: 137

Text #14

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0124. Min Act: -0.0006

Data Index: 638808 (C4 (Web Text))

Max Activating Token Index: 320

Text #15

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0118. Min Act: -0.0006

Data Index: 550949 (C4 (Web Text))

Max Activating Token Index: 85

Text #16

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0114. Min Act: -0.0006

Data Index: 84592 (C4 (Web Text))

Max Activating Token Index: 566

Text #17

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0123. Min Act: -0.0006

Data Index: 1036432 (C4 (Web Text))

Max Activating Token Index: 165

Text #18

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0116. Min Act: -0.0006

Data Index: 1344984 (C4 (Web Text))

Max Activating Token Index: 527

Text #19

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0114. Min Act: -0.0007

Data Index: 1043406 (C4 (Web Text))

Max Activating Token Index: 486