Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3877 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0758. Min Act: -0.0003

Data Index: 1483328 (Python Code)

Max Activating Token Index: 836

Text #1

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0272. Min Act: -0.0003

Data Index: 1572470 (Python Code)

Max Activating Token Index: 616

Text #2

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0270. Min Act: -0.0003

Data Index: 837331 (C4 (Web Text))

Max Activating Token Index: 824

Text #3

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0190. Min Act: -0.0003

Data Index: 835401 (C4 (Web Text))

Max Activating Token Index: 918

Text #4

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0181. Min Act: -0.0003

Data Index: 780700 (C4 (Web Text))

Max Activating Token Index: 250

Text #5

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0173. Min Act: -0.0003

Data Index: 1321307 (C4 (Web Text))

Max Activating Token Index: 863

Text #6

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0143. Min Act: -0.0003

Data Index: 1382770 (Python Code)

Max Activating Token Index: 954

Text #7

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0134. Min Act: -0.0003

Data Index: 433632 (C4 (Web Text))

Max Activating Token Index: 587

Text #8

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0134. Min Act: -0.0003

Data Index: 1420157 (Python Code)

Max Activating Token Index: 584

Text #9

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0127. Min Act: -0.0003

Data Index: 1590450 (Python Code)

Max Activating Token Index: 41

Text #10

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0131. Min Act: -0.0003

Data Index: 20188 (C4 (Web Text))

Max Activating Token Index: 78

Text #11

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0124. Min Act: -0.0003

Data Index: 1417889 (Python Code)

Max Activating Token Index: 487

Text #12

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0120. Min Act: -0.0003

Data Index: 1618636 (Python Code)

Max Activating Token Index: 299

Text #13

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0117. Min Act: -0.0003

Data Index: 1323574 (C4 (Web Text))

Max Activating Token Index: 904

Text #14

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0119. Min Act: -0.0003

Data Index: 157390 (C4 (Web Text))

Max Activating Token Index: 785

Text #15

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0114. Min Act: -0.0003

Data Index: 937283 (C4 (Web Text))

Max Activating Token Index: 132

Text #16

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0117. Min Act: -0.0003

Data Index: 1463589 (Python Code)

Max Activating Token Index: 413

Text #17

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0114. Min Act: -0.0003

Data Index: 314822 (C4 (Web Text))

Max Activating Token Index: 815

Text #18

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0111. Min Act: -0.0003

Data Index: 1372470 (Python Code)

Max Activating Token Index: 228

Text #19

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0105. Min Act: -0.0003

Data Index: 1520199 (Python Code)

Max Activating Token Index: 637