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

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

Neuron 5442 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: 1.6963. Min Range: -1.6963

Max Act: 1.6963. Min Act: -0.0002

Data Index: 1466255 (Python Code)

Max Activating Token Index: 704

Text #1

Max Range: 1.6963. Min Range: -1.6963

Max Act: 1.6213. Min Act: -0.0002

Data Index: 1570464 (Python Code)

Max Activating Token Index: 463

Text #2

Max Range: 1.6963. Min Range: -1.6963

Max Act: 1.6236. Min Act: -0.0002

Data Index: 1600163 (Python Code)

Max Activating Token Index: 758

Text #3

Max Range: 1.6963. Min Range: -1.6963

Max Act: 1.5451. Min Act: -0.0002

Data Index: 1438258 (Python Code)

Max Activating Token Index: 472

Text #4

Max Range: 1.6963. Min Range: -1.6963

Max Act: 1.5565. Min Act: -0.0002

Data Index: 1440215 (Python Code)

Max Activating Token Index: 608

Text #5

Max Range: 1.6963. Min Range: -1.6963

Max Act: 1.5461. Min Act: -0.0002

Data Index: 1579780 (Python Code)

Max Activating Token Index: 350

Text #6

Max Range: 1.6963. Min Range: -1.6963

Max Act: 1.5304. Min Act: -0.0002

Data Index: 1437770 (Python Code)

Max Activating Token Index: 139

Text #7

Max Range: 1.6963. Min Range: -1.6963

Max Act: 1.4926. Min Act: -0.0002

Data Index: 1433602 (Python Code)

Max Activating Token Index: 121

Text #8

Max Range: 1.6963. Min Range: -1.6963

Max Act: 1.4842. Min Act: -0.0002

Data Index: 1372438 (Python Code)

Max Activating Token Index: 475

Text #9

Max Range: 1.6963. Min Range: -1.6963

Max Act: 1.4461. Min Act: -0.0002

Data Index: 1563646 (Python Code)

Max Activating Token Index: 376

Text #10

Max Range: 1.6963. Min Range: -1.6963

Max Act: 1.4649. Min Act: -0.0002

Data Index: 1570064 (Python Code)

Max Activating Token Index: 930

Text #11

Max Range: 1.6963. Min Range: -1.6963

Max Act: 1.4492. Min Act: -0.0002

Data Index: 1471824 (Python Code)

Max Activating Token Index: 134

Text #12

Max Range: 1.6963. Min Range: -1.6963

Max Act: 1.4373. Min Act: -0.0002

Data Index: 1492824 (Python Code)

Max Activating Token Index: 286

Text #13

Max Range: 1.6963. Min Range: -1.6963

Max Act: 1.4170. Min Act: -0.0002

Data Index: 1424273 (Python Code)

Max Activating Token Index: 342

Text #14

Max Range: 1.6963. Min Range: -1.6963

Max Act: 1.4388. Min Act: -0.0002

Data Index: 1403527 (Python Code)

Max Activating Token Index: 209

Text #15

Max Range: 1.6963. Min Range: -1.6963

Max Act: 1.4394. Min Act: -0.0002

Data Index: 1573501 (Python Code)

Max Activating Token Index: 109

Text #16

Max Range: 1.6963. Min Range: -1.6963

Max Act: 1.4209. Min Act: -0.0002

Data Index: 1408573 (Python Code)

Max Activating Token Index: 60

Text #17

Max Range: 1.6963. Min Range: -1.6963

Max Act: 1.4464. Min Act: -0.0002

Data Index: 1476721 (Python Code)

Max Activating Token Index: 884

Text #18

Max Range: 1.6963. Min Range: -1.6963

Max Act: 1.3920. Min Act: -0.0002

Data Index: 1615702 (Python Code)

Max Activating Token Index: 60

Text #19

Max Range: 1.6963. Min Range: -1.6963

Max Act: 1.4128. Min Act: -0.0002

Data Index: 1385836 (Python Code)

Max Activating Token Index: 758