Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1401 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0145. Min Act: -0.0004

Data Index: 1563146 (Python Code)

Max Activating Token Index: 564

Text #1

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0139. Min Act: -0.0004

Data Index: 1435437 (Python Code)

Max Activating Token Index: 575

Text #2

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0138. Min Act: -0.0004

Data Index: 1334708 (C4 (Web Text))

Max Activating Token Index: 614

Text #3

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0122. Min Act: -0.0004

Data Index: 1556255 (Python Code)

Max Activating Token Index: 669

Text #4

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0124. Min Act: -0.0004

Data Index: 689349 (C4 (Web Text))

Max Activating Token Index: 955

Text #5

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0122. Min Act: -0.0004

Data Index: 873339 (C4 (Web Text))

Max Activating Token Index: 910

Text #6

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0120. Min Act: -0.0004

Data Index: 1386592 (Python Code)

Max Activating Token Index: 773

Text #7

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0119. Min Act: -0.0004

Data Index: 1369027 (Python Code)

Max Activating Token Index: 604

Text #8

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0120. Min Act: -0.0004

Data Index: 387895 (C4 (Web Text))

Max Activating Token Index: 683

Text #9

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0113. Min Act: -0.0004

Data Index: 1567235 (Python Code)

Max Activating Token Index: 789

Text #10

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0116. Min Act: -0.0004

Data Index: 1417448 (Python Code)

Max Activating Token Index: 851

Text #11

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0120. Min Act: -0.0004

Data Index: 507999 (C4 (Web Text))

Max Activating Token Index: 969

Text #12

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0123. Min Act: -0.0004

Data Index: 633466 (C4 (Web Text))

Max Activating Token Index: 867

Text #13

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0112. Min Act: -0.0004

Data Index: 92417 (C4 (Web Text))

Max Activating Token Index: 638

Text #14

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0106. Min Act: -0.0004

Data Index: 1513603 (Python Code)

Max Activating Token Index: 317

Text #15

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0111. Min Act: -0.0004

Data Index: 2909 (C4 (Web Text))

Max Activating Token Index: 831

Text #16

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0110. Min Act: -0.0004

Data Index: 1091254 (C4 (Web Text))

Max Activating Token Index: 988

Text #17

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0112. Min Act: -0.0004

Data Index: 1455089 (Python Code)

Max Activating Token Index: 712

Text #18

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0114. Min Act: -0.0004

Data Index: 1263990 (C4 (Web Text))

Max Activating Token Index: 521

Text #19

Max Range: 0.0145. Min Range: -0.0145

Max Act: 0.0111. Min Act: -0.0004

Data Index: 304828 (C4 (Web Text))

Max Activating Token Index: 1008