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

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

Neuron 3617 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3235. Min Range: -1.3235

Max Act: 1.3235. Min Act: -0.0001

Data Index: 542550 (C4 (Web Text))

Max Activating Token Index: 37

Text #1

Max Range: 1.3235. Min Range: -1.3235

Max Act: 1.3018. Min Act: -0.0001

Data Index: 148277 (C4 (Web Text))

Max Activating Token Index: 930

Text #2

Max Range: 1.3235. Min Range: -1.3235

Max Act: 1.2323. Min Act: -0.0001

Data Index: 287811 (C4 (Web Text))

Max Activating Token Index: 187

Text #3

Max Range: 1.3235. Min Range: -1.3235

Max Act: 1.2126. Min Act: -0.0000

Data Index: 733345 (C4 (Web Text))

Max Activating Token Index: 348

Text #4

Max Range: 1.3235. Min Range: -1.3235

Max Act: 1.1790. Min Act: -0.0001

Data Index: 88008 (C4 (Web Text))

Max Activating Token Index: 765

Text #5

Max Range: 1.3235. Min Range: -1.3235

Max Act: 1.1431. Min Act: -0.0001

Data Index: 85446 (C4 (Web Text))

Max Activating Token Index: 77

Text #6

Max Range: 1.3235. Min Range: -1.3235

Max Act: 1.1710. Min Act: -0.0001

Data Index: 67074 (C4 (Web Text))

Max Activating Token Index: 293

Text #7

Max Range: 1.3235. Min Range: -1.3235

Max Act: 1.0184. Min Act: -0.0001

Data Index: 589668 (C4 (Web Text))

Max Activating Token Index: 462

Text #8

Max Range: 1.3235. Min Range: -1.3235

Max Act: 1.0157. Min Act: -0.0001

Data Index: 1067764 (C4 (Web Text))

Max Activating Token Index: 358

Text #9

Max Range: 1.3235. Min Range: -1.3235

Max Act: 1.0673. Min Act: -0.0001

Data Index: 1225109 (C4 (Web Text))

Max Activating Token Index: 951

Text #10

Max Range: 1.3235. Min Range: -1.3235

Max Act: 1.1293. Min Act: -0.0001

Data Index: 33300 (C4 (Web Text))

Max Activating Token Index: 126

Text #11

Max Range: 1.3235. Min Range: -1.3235

Max Act: 1.0971. Min Act: -0.0001

Data Index: 747273 (C4 (Web Text))

Max Activating Token Index: 871

Text #12

Max Range: 1.3235. Min Range: -1.3235

Max Act: 1.0307. Min Act: -0.0000

Data Index: 637546 (C4 (Web Text))

Max Activating Token Index: 21

Text #13

Max Range: 1.3235. Min Range: -1.3235

Max Act: 1.0047. Min Act: -0.0001

Data Index: 1271105 (C4 (Web Text))

Max Activating Token Index: 910

Text #14

Max Range: 1.3235. Min Range: -1.3235

Max Act: 0.9998. Min Act: -0.0001

Data Index: 1114093 (C4 (Web Text))

Max Activating Token Index: 768

Text #15

Max Range: 1.3235. Min Range: -1.3235

Max Act: 0.9499. Min Act: -0.0001

Data Index: 581948 (C4 (Web Text))

Max Activating Token Index: 396

Text #16

Max Range: 1.3235. Min Range: -1.3235

Max Act: 0.9713. Min Act: -0.0001

Data Index: 632114 (C4 (Web Text))

Max Activating Token Index: 903

Text #17

Max Range: 1.3235. Min Range: -1.3235

Max Act: 0.9651. Min Act: -0.0001

Data Index: 292527 (C4 (Web Text))

Max Activating Token Index: 218

Text #18

Max Range: 1.3235. Min Range: -1.3235

Max Act: 0.9588. Min Act: -0.0001

Data Index: 545428 (C4 (Web Text))

Max Activating Token Index: 334

Text #19

Max Range: 1.3235. Min Range: -1.3235

Max Act: 0.9250. Min Act: -0.0001

Data Index: 379776 (C4 (Web Text))

Max Activating Token Index: 591