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

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

Neuron 2082 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: 0.2409. Min Range: -0.2409

Max Act: 0.2409. Min Act: -0.0002

Data Index: 38922 (C4 (Web Text))

Max Activating Token Index: 282

Text #1

Max Range: 0.2409. Min Range: -0.2409

Max Act: 0.2285. Min Act: -0.0002

Data Index: 81181 (C4 (Web Text))

Max Activating Token Index: 833

Text #2

Max Range: 0.2409. Min Range: -0.2409

Max Act: 0.2155. Min Act: -0.0002

Data Index: 26532 (C4 (Web Text))

Max Activating Token Index: 192

Text #3

Max Range: 0.2409. Min Range: -0.2409

Max Act: 0.2073. Min Act: -0.0002

Data Index: 1287358 (C4 (Web Text))

Max Activating Token Index: 229

Text #4

Max Range: 0.2409. Min Range: -0.2409

Max Act: 0.1985. Min Act: -0.0002

Data Index: 968044 (C4 (Web Text))

Max Activating Token Index: 517

Text #5

Max Range: 0.2409. Min Range: -0.2409

Max Act: 0.1955. Min Act: -0.0002

Data Index: 285426 (C4 (Web Text))

Max Activating Token Index: 587

Text #6

Max Range: 0.2409. Min Range: -0.2409

Max Act: 0.1900. Min Act: -0.0002

Data Index: 305014 (C4 (Web Text))

Max Activating Token Index: 121

Text #7

Max Range: 0.2409. Min Range: -0.2409

Max Act: 0.1835. Min Act: -0.0002

Data Index: 831595 (C4 (Web Text))

Max Activating Token Index: 712

Text #8

Max Range: 0.2409. Min Range: -0.2409

Max Act: 0.1768. Min Act: -0.0002

Data Index: 178197 (C4 (Web Text))

Max Activating Token Index: 711

Text #9

Max Range: 0.2409. Min Range: -0.2409

Max Act: 0.1741. Min Act: -0.0002

Data Index: 997383 (C4 (Web Text))

Max Activating Token Index: 85

Text #10

Max Range: 0.2409. Min Range: -0.2409

Max Act: 0.1610. Min Act: -0.0002

Data Index: 1250024 (C4 (Web Text))

Max Activating Token Index: 82

Text #11

Max Range: 0.2409. Min Range: -0.2409

Max Act: 0.1598. Min Act: -0.0002

Data Index: 545746 (C4 (Web Text))

Max Activating Token Index: 269

Text #12

Max Range: 0.2409. Min Range: -0.2409

Max Act: 0.1540. Min Act: -0.0002

Data Index: 657605 (C4 (Web Text))

Max Activating Token Index: 980

Text #13

Max Range: 0.2409. Min Range: -0.2409

Max Act: 0.1578. Min Act: -0.0002

Data Index: 336258 (C4 (Web Text))

Max Activating Token Index: 511

Text #14

Max Range: 0.2409. Min Range: -0.2409

Max Act: 0.1517. Min Act: -0.0002

Data Index: 38102 (C4 (Web Text))

Max Activating Token Index: 291

Text #15

Max Range: 0.2409. Min Range: -0.2409

Max Act: 0.1437. Min Act: -0.0002

Data Index: 40547 (C4 (Web Text))

Max Activating Token Index: 362

Text #16

Max Range: 0.2409. Min Range: -0.2409

Max Act: 0.1410. Min Act: -0.0002

Data Index: 483680 (C4 (Web Text))

Max Activating Token Index: 480

Text #17

Max Range: 0.2409. Min Range: -0.2409

Max Act: 0.1287. Min Act: -0.0002

Data Index: 413477 (C4 (Web Text))

Max Activating Token Index: 128

Text #18

Max Range: 0.2409. Min Range: -0.2409

Max Act: 0.1270. Min Act: -0.0002

Data Index: 1473660 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 0.2409. Min Range: -0.2409

Max Act: 0.1347. Min Act: -0.0002

Data Index: 1313789 (C4 (Web Text))

Max Activating Token Index: 222