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

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

Neuron 1488 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0525. Min Act: -0.0006

Data Index: 314822 (C4 (Web Text))

Max Activating Token Index: 819

Text #1

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0359. Min Act: -0.0006

Data Index: 837331 (C4 (Web Text))

Max Activating Token Index: 811

Text #2

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0296. Min Act: -0.0006

Data Index: 1422031 (Python Code)

Max Activating Token Index: 239

Text #3

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0214. Min Act: -0.0005

Data Index: 1318778 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0157. Min Act: -0.0006

Data Index: 1382770 (Python Code)

Max Activating Token Index: 958

Text #5

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0163. Min Act: -0.0006

Data Index: 1388406 (Python Code)

Max Activating Token Index: 857

Text #6

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0149. Min Act: -0.0006

Data Index: 780700 (C4 (Web Text))

Max Activating Token Index: 248

Text #7

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0148. Min Act: -0.0006

Data Index: 1609712 (Python Code)

Max Activating Token Index: 193

Text #8

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0149. Min Act: -0.0006

Data Index: 1105038 (C4 (Web Text))

Max Activating Token Index: 861

Text #9

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0141. Min Act: -0.0006

Data Index: 422869 (C4 (Web Text))

Max Activating Token Index: 95

Text #10

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0139. Min Act: -0.0006

Data Index: 1427905 (Python Code)

Max Activating Token Index: 185

Text #11

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0129. Min Act: -0.0006

Data Index: 1411172 (Python Code)

Max Activating Token Index: 227

Text #12

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0143. Min Act: -0.0005

Data Index: 901669 (C4 (Web Text))

Max Activating Token Index: 977

Text #13

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0135. Min Act: -0.0006

Data Index: 1512699 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0125. Min Act: -0.0006

Data Index: 1572470 (Python Code)

Max Activating Token Index: 605

Text #15

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0102. Min Act: -0.0006

Data Index: 1114942 (C4 (Web Text))

Max Activating Token Index: 52

Text #16

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0127. Min Act: -0.0006

Data Index: 1001513 (C4 (Web Text))

Max Activating Token Index: 698

Text #17

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0109. Min Act: -0.0005

Data Index: 1281704 (C4 (Web Text))

Max Activating Token Index: 329

Text #18

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0120. Min Act: -0.0006

Data Index: 592846 (C4 (Web Text))

Max Activating Token Index: 351

Text #19

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0116. Min Act: -0.0006

Data Index: 1406563 (Python Code)

Max Activating Token Index: 954