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

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

Neuron 5610 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.8651. Min Act: -0.0002

Data Index: 1043358 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.8893. Min Act: -0.0002

Data Index: 244687 (C4 (Web Text))

Max Activating Token Index: 65

Text #2

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.8618. Min Act: -0.0002

Data Index: 255437 (C4 (Web Text))

Max Activating Token Index: 767

Text #3

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.8357. Min Act: -0.0002

Data Index: 1023307 (C4 (Web Text))

Max Activating Token Index: 67

Text #4

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.8263. Min Act: -0.0003

Data Index: 447838 (C4 (Web Text))

Max Activating Token Index: 28

Text #5

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.8177. Min Act: -0.0002

Data Index: 1030626 (C4 (Web Text))

Max Activating Token Index: 710

Text #6

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.7995. Min Act: -0.0002

Data Index: 1209455 (C4 (Web Text))

Max Activating Token Index: 16

Text #7

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.7993. Min Act: -0.0002

Data Index: 1056064 (C4 (Web Text))

Max Activating Token Index: 10

Text #8

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.7951. Min Act: -0.0002

Data Index: 473108 (C4 (Web Text))

Max Activating Token Index: 22

Text #9

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.7786. Min Act: -0.0002

Data Index: 505905 (C4 (Web Text))

Max Activating Token Index: 37

Text #10

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.7367. Min Act: -0.0002

Data Index: 1314206 (C4 (Web Text))

Max Activating Token Index: 36

Text #11

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.7490. Min Act: -0.0002

Data Index: 1284802 (C4 (Web Text))

Max Activating Token Index: 74

Text #12

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.7497. Min Act: -0.0002

Data Index: 1284995 (C4 (Web Text))

Max Activating Token Index: 840

Text #13

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.7204. Min Act: -0.0002

Data Index: 120480 (C4 (Web Text))

Max Activating Token Index: 720

Text #14

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.7300. Min Act: -0.0002

Data Index: 1038171 (C4 (Web Text))

Max Activating Token Index: 190

Text #15

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.7276. Min Act: -0.0003

Data Index: 266688 (C4 (Web Text))

Max Activating Token Index: 493

Text #16

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.7217. Min Act: -0.0003

Data Index: 678173 (C4 (Web Text))

Max Activating Token Index: 521

Text #17

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.7177. Min Act: -0.0002

Data Index: 1236209 (C4 (Web Text))

Max Activating Token Index: 182

Text #18

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.7249. Min Act: -0.0002

Data Index: 581285 (C4 (Web Text))

Max Activating Token Index: 394

Text #19

Max Range: 0.8893. Min Range: -0.8893

Max Act: 0.7167. Min Act: -0.0002

Data Index: 1163272 (C4 (Web Text))

Max Activating Token Index: 305