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

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

Neuron 234 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: 0.0125. Min Range: -0.0125

Max Act: 0.0125. Min Act: -0.0002

Data Index: 1327291 (C4 (Web Text))

Max Activating Token Index: 7

Text #1

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0116. Min Act: -0.0002

Data Index: 811680 (C4 (Web Text))

Max Activating Token Index: 9

Text #2

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0118. Min Act: -0.0002

Data Index: 769832 (C4 (Web Text))

Max Activating Token Index: 41

Text #3

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0115. Min Act: -0.0002

Data Index: 1184423 (C4 (Web Text))

Max Activating Token Index: 3

Text #4

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0116. Min Act: -0.0002

Data Index: 1025486 (C4 (Web Text))

Max Activating Token Index: 395

Text #5

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0116. Min Act: -0.0002

Data Index: 847921 (C4 (Web Text))

Max Activating Token Index: 642

Text #6

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0115. Min Act: -0.0002

Data Index: 434742 (C4 (Web Text))

Max Activating Token Index: 167

Text #7

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0114. Min Act: -0.0002

Data Index: 291462 (C4 (Web Text))

Max Activating Token Index: 512

Text #8

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0114. Min Act: -0.0002

Data Index: 1149912 (C4 (Web Text))

Max Activating Token Index: 643

Text #9

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0114. Min Act: -0.0002

Data Index: 386346 (C4 (Web Text))

Max Activating Token Index: 536

Text #10

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0114. Min Act: -0.0002

Data Index: 519156 (C4 (Web Text))

Max Activating Token Index: 26

Text #11

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0111. Min Act: -0.0002

Data Index: 962803 (C4 (Web Text))

Max Activating Token Index: 68

Text #12

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0113. Min Act: -0.0002

Data Index: 931396 (C4 (Web Text))

Max Activating Token Index: 549

Text #13

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0113. Min Act: -0.0002

Data Index: 199007 (C4 (Web Text))

Max Activating Token Index: 166

Text #14

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0113. Min Act: -0.0002

Data Index: 395457 (C4 (Web Text))

Max Activating Token Index: 726

Text #15

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0113. Min Act: -0.0002

Data Index: 809668 (C4 (Web Text))

Max Activating Token Index: 621

Text #16

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0113. Min Act: -0.0002

Data Index: 119477 (C4 (Web Text))

Max Activating Token Index: 122

Text #17

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0113. Min Act: -0.0002

Data Index: 1214235 (C4 (Web Text))

Max Activating Token Index: 15

Text #18

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0114. Min Act: -0.0002

Data Index: 458828 (C4 (Web Text))

Max Activating Token Index: 645

Text #19

Max Range: 0.0125. Min Range: -0.0125

Max Act: 0.0112. Min Act: -0.0002

Data Index: 1203161 (C4 (Web Text))

Max Activating Token Index: 532