Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4579 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0169. Min Act: -0.0002

Data Index: 1056108 (C4 (Web Text))

Max Activating Token Index: 622

Text #1

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0129. Min Act: -0.0002

Data Index: 116348 (C4 (Web Text))

Max Activating Token Index: 794

Text #2

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0127. Min Act: -0.0002

Data Index: 704598 (C4 (Web Text))

Max Activating Token Index: 226

Text #3

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0133. Min Act: -0.0002

Data Index: 1152812 (C4 (Web Text))

Max Activating Token Index: 619

Text #4

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0116. Min Act: -0.0002

Data Index: 108223 (C4 (Web Text))

Max Activating Token Index: 466

Text #5

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0114. Min Act: -0.0002

Data Index: 982312 (C4 (Web Text))

Max Activating Token Index: 789

Text #6

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0112. Min Act: -0.0002

Data Index: 1550681 (Python Code)

Max Activating Token Index: 465

Text #7

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0110. Min Act: -0.0002

Data Index: 1365480 (Python Code)

Max Activating Token Index: 295

Text #8

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0112. Min Act: -0.0002

Data Index: 214502 (C4 (Web Text))

Max Activating Token Index: 525

Text #9

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0114. Min Act: -0.0002

Data Index: 1259614 (C4 (Web Text))

Max Activating Token Index: 332

Text #10

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0111. Min Act: -0.0002

Data Index: 1602593 (Python Code)

Max Activating Token Index: 853

Text #11

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0107. Min Act: -0.0002

Data Index: 455073 (C4 (Web Text))

Max Activating Token Index: 228

Text #12

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0105. Min Act: -0.0002

Data Index: 1377092 (Python Code)

Max Activating Token Index: 929

Text #13

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0104. Min Act: -0.0002

Data Index: 1581390 (Python Code)

Max Activating Token Index: 778

Text #14

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0102. Min Act: -0.0002

Data Index: 210010 (C4 (Web Text))

Max Activating Token Index: 465

Text #15

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0101. Min Act: -0.0002

Data Index: 1118703 (C4 (Web Text))

Max Activating Token Index: 590

Text #16

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0098. Min Act: -0.0002

Data Index: 568511 (C4 (Web Text))

Max Activating Token Index: 745

Text #17

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0098. Min Act: -0.0002

Data Index: 90407 (C4 (Web Text))

Max Activating Token Index: 673

Text #18

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0104. Min Act: -0.0002

Data Index: 544817 (C4 (Web Text))

Max Activating Token Index: 748

Text #19

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0098. Min Act: -0.0002

Data Index: 1383700 (Python Code)

Max Activating Token Index: 536