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

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

Neuron 1037 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: 0.0136. Min Range: -0.0136

Max Act: 0.0136. Min Act: -0.0006

Data Index: 391895 (C4 (Web Text))

Max Activating Token Index: 315

Text #1

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0125. Min Act: -0.0006

Data Index: 58020 (C4 (Web Text))

Max Activating Token Index: 999

Text #2

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0122. Min Act: -0.0006

Data Index: 1551882 (Python Code)

Max Activating Token Index: 646

Text #3

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0121. Min Act: -0.0006

Data Index: 1361452 (Python Code)

Max Activating Token Index: 970

Text #4

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0117. Min Act: -0.0005

Data Index: 1646580 (Python Code)

Max Activating Token Index: 616

Text #5

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0117. Min Act: -0.0006

Data Index: 1423689 (Python Code)

Max Activating Token Index: 944

Text #6

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0117. Min Act: -0.0006

Data Index: 351105 (C4 (Web Text))

Max Activating Token Index: 914

Text #7

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0114. Min Act: -0.0006

Data Index: 1488988 (Python Code)

Max Activating Token Index: 702

Text #8

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0116. Min Act: -0.0006

Data Index: 1281777 (C4 (Web Text))

Max Activating Token Index: 349

Text #9

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0116. Min Act: -0.0006

Data Index: 1529045 (Python Code)

Max Activating Token Index: 619

Text #10

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0114. Min Act: -0.0006

Data Index: 1601703 (Python Code)

Max Activating Token Index: 586

Text #11

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0113. Min Act: -0.0006

Data Index: 26870 (C4 (Web Text))

Max Activating Token Index: 575

Text #12

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0112. Min Act: -0.0006

Data Index: 1434816 (Python Code)

Max Activating Token Index: 542

Text #13

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0111. Min Act: -0.0006

Data Index: 1153465 (C4 (Web Text))

Max Activating Token Index: 944

Text #14

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0109. Min Act: -0.0006

Data Index: 162204 (C4 (Web Text))

Max Activating Token Index: 824

Text #15

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0108. Min Act: -0.0006

Data Index: 376412 (C4 (Web Text))

Max Activating Token Index: 974

Text #16

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0111. Min Act: -0.0006

Data Index: 1590942 (Python Code)

Max Activating Token Index: 982

Text #17

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0103. Min Act: -0.0006

Data Index: 1515405 (Python Code)

Max Activating Token Index: 954

Text #18

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0110. Min Act: -0.0006

Data Index: 1535064 (Python Code)

Max Activating Token Index: 544

Text #19

Max Range: 0.0136. Min Range: -0.0136

Max Act: 0.0108. Min Act: -0.0006

Data Index: 214657 (C4 (Web Text))

Max Activating Token Index: 808