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

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

Neuron 1946 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0162. Min Act: -0.0006

Data Index: 615523 (C4 (Web Text))

Max Activating Token Index: 579

Text #1

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0154. Min Act: -0.0006

Data Index: 634850 (C4 (Web Text))

Max Activating Token Index: 328

Text #2

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0142. Min Act: -0.0006

Data Index: 997168 (C4 (Web Text))

Max Activating Token Index: 146

Text #3

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0141. Min Act: -0.0006

Data Index: 22347 (C4 (Web Text))

Max Activating Token Index: 334

Text #4

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0137. Min Act: -0.0006

Data Index: 1002126 (C4 (Web Text))

Max Activating Token Index: 755

Text #5

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0127. Min Act: -0.0006

Data Index: 516916 (C4 (Web Text))

Max Activating Token Index: 507

Text #6

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0129. Min Act: -0.0006

Data Index: 775000 (C4 (Web Text))

Max Activating Token Index: 672

Text #7

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0122. Min Act: -0.0006

Data Index: 830908 (C4 (Web Text))

Max Activating Token Index: 192

Text #8

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0135. Min Act: -0.0006

Data Index: 1235457 (C4 (Web Text))

Max Activating Token Index: 999

Text #9

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0131. Min Act: -0.0006

Data Index: 475624 (C4 (Web Text))

Max Activating Token Index: 684

Text #10

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0125. Min Act: -0.0006

Data Index: 594828 (C4 (Web Text))

Max Activating Token Index: 508

Text #11

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0113. Min Act: -0.0006

Data Index: 1216351 (C4 (Web Text))

Max Activating Token Index: 1019

Text #12

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0127. Min Act: -0.0006

Data Index: 196054 (C4 (Web Text))

Max Activating Token Index: 590

Text #13

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0125. Min Act: -0.0006

Data Index: 382304 (C4 (Web Text))

Max Activating Token Index: 74

Text #14

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0116. Min Act: -0.0006

Data Index: 691362 (C4 (Web Text))

Max Activating Token Index: 498

Text #15

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0126. Min Act: -0.0006

Data Index: 1293293 (C4 (Web Text))

Max Activating Token Index: 42

Text #16

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0127. Min Act: -0.0006

Data Index: 1119101 (C4 (Web Text))

Max Activating Token Index: 446

Text #17

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0118. Min Act: -0.0006

Data Index: 1127679 (C4 (Web Text))

Max Activating Token Index: 300

Text #18

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0114. Min Act: -0.0006

Data Index: 727891 (C4 (Web Text))

Max Activating Token Index: 291

Text #19

Max Range: 0.0162. Min Range: -0.0162

Max Act: 0.0110. Min Act: -0.0006

Data Index: 20612 (C4 (Web Text))

Max Activating Token Index: 482