Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1632 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0140. Min Act: -0.0005

Data Index: 580720 (C4 (Web Text))

Max Activating Token Index: 519

Text #1

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0132. Min Act: -0.0005

Data Index: 1246450 (C4 (Web Text))

Max Activating Token Index: 336

Text #2

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0125. Min Act: -0.0005

Data Index: 394773 (C4 (Web Text))

Max Activating Token Index: 927

Text #3

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0126. Min Act: -0.0005

Data Index: 268883 (C4 (Web Text))

Max Activating Token Index: 258

Text #4

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0126. Min Act: -0.0005

Data Index: 481183 (C4 (Web Text))

Max Activating Token Index: 33

Text #5

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0122. Min Act: -0.0005

Data Index: 1207124 (C4 (Web Text))

Max Activating Token Index: 794

Text #6

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0127. Min Act: -0.0005

Data Index: 354378 (C4 (Web Text))

Max Activating Token Index: 956

Text #7

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0123. Min Act: -0.0005

Data Index: 1314247 (C4 (Web Text))

Max Activating Token Index: 314

Text #8

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0123. Min Act: -0.0005

Data Index: 1330416 (C4 (Web Text))

Max Activating Token Index: 653

Text #9

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0120. Min Act: -0.0005

Data Index: 107982 (C4 (Web Text))

Max Activating Token Index: 421

Text #10

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0123. Min Act: -0.0006

Data Index: 754220 (C4 (Web Text))

Max Activating Token Index: 38

Text #11

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0123. Min Act: -0.0005

Data Index: 265115 (C4 (Web Text))

Max Activating Token Index: 450

Text #12

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0122. Min Act: -0.0005

Data Index: 81698 (C4 (Web Text))

Max Activating Token Index: 802

Text #13

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0122. Min Act: -0.0005

Data Index: 309768 (C4 (Web Text))

Max Activating Token Index: 112

Text #14

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0122. Min Act: -0.0005

Data Index: 1103388 (C4 (Web Text))

Max Activating Token Index: 689

Text #15

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0120. Min Act: -0.0005

Data Index: 96681 (C4 (Web Text))

Max Activating Token Index: 281

Text #16

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0123. Min Act: -0.0005

Data Index: 270882 (C4 (Web Text))

Max Activating Token Index: 831

Text #17

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0120. Min Act: -0.0005

Data Index: 791006 (C4 (Web Text))

Max Activating Token Index: 817

Text #18

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0120. Min Act: -0.0005

Data Index: 180901 (C4 (Web Text))

Max Activating Token Index: 690

Text #19

Max Range: 0.0140. Min Range: -0.0140

Max Act: 0.0120. Min Act: -0.0005

Data Index: 186782 (C4 (Web Text))

Max Activating Token Index: 557