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

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

Neuron 1523 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0146. Min Act: -0.0004

Data Index: 1506897 (Python Code)

Max Activating Token Index: 914

Text #1

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0141. Min Act: -0.0005

Data Index: 418533 (C4 (Web Text))

Max Activating Token Index: 238

Text #2

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0137. Min Act: -0.0005

Data Index: 1304150 (C4 (Web Text))

Max Activating Token Index: 893

Text #3

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0126. Min Act: -0.0005

Data Index: 1302206 (C4 (Web Text))

Max Activating Token Index: 813

Text #4

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0117. Min Act: -0.0005

Data Index: 1477549 (Python Code)

Max Activating Token Index: 479

Text #5

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0116. Min Act: -0.0005

Data Index: 25372 (C4 (Web Text))

Max Activating Token Index: 293

Text #6

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0118. Min Act: -0.0005

Data Index: 914280 (C4 (Web Text))

Max Activating Token Index: 722

Text #7

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0113. Min Act: -0.0005

Data Index: 516199 (C4 (Web Text))

Max Activating Token Index: 400

Text #8

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0120. Min Act: -0.0005

Data Index: 1619787 (Python Code)

Max Activating Token Index: 734

Text #9

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0113. Min Act: -0.0005

Data Index: 1391042 (Python Code)

Max Activating Token Index: 10

Text #10

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0113. Min Act: -0.0005

Data Index: 543039 (C4 (Web Text))

Max Activating Token Index: 420

Text #11

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0112. Min Act: -0.0005

Data Index: 1094473 (C4 (Web Text))

Max Activating Token Index: 985

Text #12

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0108. Min Act: -0.0005

Data Index: 85609 (C4 (Web Text))

Max Activating Token Index: 397

Text #13

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0112. Min Act: -0.0005

Data Index: 747531 (C4 (Web Text))

Max Activating Token Index: 911

Text #14

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0108. Min Act: -0.0005

Data Index: 1299513 (C4 (Web Text))

Max Activating Token Index: 1012

Text #15

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0104. Min Act: -0.0005

Data Index: 1392333 (Python Code)

Max Activating Token Index: 552

Text #16

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0102. Min Act: -0.0005

Data Index: 306641 (C4 (Web Text))

Max Activating Token Index: 960

Text #17

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0101. Min Act: -0.0005

Data Index: 891331 (C4 (Web Text))

Max Activating Token Index: 33

Text #18

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0098. Min Act: -0.0005

Data Index: 1551144 (Python Code)

Max Activating Token Index: 466

Text #19

Max Range: 0.0146. Min Range: -0.0146

Max Act: 0.0100. Min Act: -0.0005

Data Index: 1586129 (Python Code)

Max Activating Token Index: 859