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

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

Neuron 3036 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0007. Min Range: -1.0007

Max Act: 1.0007. Min Act: -0.0001

Data Index: 1479177 (Python Code)

Max Activating Token Index: 382

Text #1

Max Range: 1.0007. Min Range: -1.0007

Max Act: 0.9955. Min Act: -0.0001

Data Index: 1443674 (Python Code)

Max Activating Token Index: 683

Text #2

Max Range: 1.0007. Min Range: -1.0007

Max Act: 0.8806. Min Act: -0.0001

Data Index: 1389721 (Python Code)

Max Activating Token Index: 870

Text #3

Max Range: 1.0007. Min Range: -1.0007

Max Act: 0.8721. Min Act: -0.0001

Data Index: 1413568 (Python Code)

Max Activating Token Index: 642

Text #4

Max Range: 1.0007. Min Range: -1.0007

Max Act: 0.8212. Min Act: -0.0001

Data Index: 1435935 (Python Code)

Max Activating Token Index: 879

Text #5

Max Range: 1.0007. Min Range: -1.0007

Max Act: 0.9065. Min Act: -0.0001

Data Index: 1442489 (Python Code)

Max Activating Token Index: 367

Text #6

Max Range: 1.0007. Min Range: -1.0007

Max Act: 0.8759. Min Act: -0.0001

Data Index: 1628664 (Python Code)

Max Activating Token Index: 509

Text #7

Max Range: 1.0007. Min Range: -1.0007

Max Act: 0.9028. Min Act: -0.0001

Data Index: 1465921 (Python Code)

Max Activating Token Index: 686

Text #8

Max Range: 1.0007. Min Range: -1.0007

Max Act: 0.8287. Min Act: -0.0001

Data Index: 1643496 (Python Code)

Max Activating Token Index: 842

Text #9

Max Range: 1.0007. Min Range: -1.0007

Max Act: 0.8525. Min Act: -0.0001

Data Index: 1545872 (Python Code)

Max Activating Token Index: 313

Text #10

Max Range: 1.0007. Min Range: -1.0007

Max Act: 0.8014. Min Act: -0.0001

Data Index: 1635606 (Python Code)

Max Activating Token Index: 767

Text #11

Max Range: 1.0007. Min Range: -1.0007

Max Act: 0.8231. Min Act: -0.0001

Data Index: 1396408 (Python Code)

Max Activating Token Index: 135

Text #12

Max Range: 1.0007. Min Range: -1.0007

Max Act: 0.7454. Min Act: -0.0001

Data Index: 1402155 (Python Code)

Max Activating Token Index: 767

Text #13

Max Range: 1.0007. Min Range: -1.0007

Max Act: 0.7771. Min Act: -0.0001

Data Index: 1566941 (Python Code)

Max Activating Token Index: 231

Text #14

Max Range: 1.0007. Min Range: -1.0007

Max Act: 0.8328. Min Act: -0.0001

Data Index: 1560050 (Python Code)

Max Activating Token Index: 345

Text #15

Max Range: 1.0007. Min Range: -1.0007

Max Act: 0.7079. Min Act: -0.0001

Data Index: 1392566 (Python Code)

Max Activating Token Index: 793

Text #16

Max Range: 1.0007. Min Range: -1.0007

Max Act: 0.8285. Min Act: -0.0001

Data Index: 1363012 (Python Code)

Max Activating Token Index: 481

Text #17

Max Range: 1.0007. Min Range: -1.0007

Max Act: 0.7835. Min Act: -0.0001

Data Index: 1577368 (Python Code)

Max Activating Token Index: 526

Text #18

Max Range: 1.0007. Min Range: -1.0007

Max Act: 0.7973. Min Act: -0.0001

Data Index: 1383872 (Python Code)

Max Activating Token Index: 204

Text #19

Max Range: 1.0007. Min Range: -1.0007

Max Act: 0.7343. Min Act: -0.0001

Data Index: 1636371 (Python Code)

Max Activating Token Index: 403