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

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

Neuron 1591 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0135. Min Act: -0.0005

Data Index: 828733 (C4 (Web Text))

Max Activating Token Index: 870

Text #1

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0129. Min Act: -0.0005

Data Index: 321097 (C4 (Web Text))

Max Activating Token Index: 148

Text #2

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0127. Min Act: -0.0005

Data Index: 496198 (C4 (Web Text))

Max Activating Token Index: 958

Text #3

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0127. Min Act: -0.0005

Data Index: 172306 (C4 (Web Text))

Max Activating Token Index: 212

Text #4

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0121. Min Act: -0.0005

Data Index: 571713 (C4 (Web Text))

Max Activating Token Index: 234

Text #5

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0122. Min Act: -0.0005

Data Index: 152888 (C4 (Web Text))

Max Activating Token Index: 970

Text #6

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0118. Min Act: -0.0004

Data Index: 398597 (C4 (Web Text))

Max Activating Token Index: 332

Text #7

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0120. Min Act: -0.0005

Data Index: 924424 (C4 (Web Text))

Max Activating Token Index: 239

Text #8

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0118. Min Act: -0.0005

Data Index: 542490 (C4 (Web Text))

Max Activating Token Index: 680

Text #9

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0113. Min Act: -0.0005

Data Index: 474619 (C4 (Web Text))

Max Activating Token Index: 149

Text #10

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0114. Min Act: -0.0004

Data Index: 773122 (C4 (Web Text))

Max Activating Token Index: 756

Text #11

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0112. Min Act: -0.0005

Data Index: 241536 (C4 (Web Text))

Max Activating Token Index: 162

Text #12

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0117. Min Act: -0.0004

Data Index: 1296335 (C4 (Web Text))

Max Activating Token Index: 231

Text #13

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0114. Min Act: -0.0005

Data Index: 159232 (C4 (Web Text))

Max Activating Token Index: 482

Text #14

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0108. Min Act: -0.0005

Data Index: 931698 (C4 (Web Text))

Max Activating Token Index: 459

Text #15

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0112. Min Act: -0.0004

Data Index: 239799 (C4 (Web Text))

Max Activating Token Index: 165

Text #16

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0113. Min Act: -0.0005

Data Index: 1340221 (C4 (Web Text))

Max Activating Token Index: 244

Text #17

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0110. Min Act: -0.0005

Data Index: 911234 (C4 (Web Text))

Max Activating Token Index: 845

Text #18

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0103. Min Act: -0.0005

Data Index: 1292570 (C4 (Web Text))

Max Activating Token Index: 290

Text #19

Max Range: 0.0135. Min Range: -0.0135

Max Act: 0.0108. Min Act: -0.0004

Data Index: 920081 (C4 (Web Text))

Max Activating Token Index: 867