Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3797 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.8683. Min Range: -2.8683

Max Act: 2.8108. Min Act: -0.0000

Data Index: 1445544 (Python Code)

Max Activating Token Index: 840

Text #1

Max Range: 2.8683. Min Range: -2.8683

Max Act: 2.8488. Min Act: -0.0000

Data Index: 1426182 (Python Code)

Max Activating Token Index: 359

Text #2

Max Range: 2.8683. Min Range: -2.8683

Max Act: 2.8683. Min Act: -0.0000

Data Index: 1419320 (Python Code)

Max Activating Token Index: 136

Text #3

Max Range: 2.8683. Min Range: -2.8683

Max Act: 2.6287. Min Act: -0.0000

Data Index: 1494768 (Python Code)

Max Activating Token Index: 120

Text #4

Max Range: 2.8683. Min Range: -2.8683

Max Act: 2.2917. Min Act: -0.0000

Data Index: 1525004 (Python Code)

Max Activating Token Index: 688

Text #5

Max Range: 2.8683. Min Range: -2.8683

Max Act: 2.0341. Min Act: -0.0000

Data Index: 1637149 (Python Code)

Max Activating Token Index: 294

Text #6

Max Range: 2.8683. Min Range: -2.8683

Max Act: 2.4130. Min Act: -0.0000

Data Index: 1565739 (Python Code)

Max Activating Token Index: 710

Text #7

Max Range: 2.8683. Min Range: -2.8683

Max Act: 2.3139. Min Act: -0.0000

Data Index: 1549851 (Python Code)

Max Activating Token Index: 289

Text #8

Max Range: 2.8683. Min Range: -2.8683

Max Act: 2.3340. Min Act: -0.0000

Data Index: 1597970 (Python Code)

Max Activating Token Index: 322

Text #9

Max Range: 2.8683. Min Range: -2.8683

Max Act: 2.1704. Min Act: -0.0000

Data Index: 1586668 (Python Code)

Max Activating Token Index: 471

Text #10

Max Range: 2.8683. Min Range: -2.8683

Max Act: 2.1407. Min Act: -0.0000

Data Index: 1610991 (Python Code)

Max Activating Token Index: 227

Text #11

Max Range: 2.8683. Min Range: -2.8683

Max Act: 2.0819. Min Act: -0.0000

Data Index: 1632560 (Python Code)

Max Activating Token Index: 72

Text #12

Max Range: 2.8683. Min Range: -2.8683

Max Act: 2.2068. Min Act: -0.0000

Data Index: 1645494 (Python Code)

Max Activating Token Index: 975

Text #13

Max Range: 2.8683. Min Range: -2.8683

Max Act: 2.2985. Min Act: -0.0000

Data Index: 1556872 (Python Code)

Max Activating Token Index: 104

Text #14

Max Range: 2.8683. Min Range: -2.8683

Max Act: 2.0022. Min Act: -0.0000

Data Index: 1467173 (Python Code)

Max Activating Token Index: 885

Text #15

Max Range: 2.8683. Min Range: -2.8683

Max Act: 2.1915. Min Act: -0.0000

Data Index: 1448248 (Python Code)

Max Activating Token Index: 361

Text #16

Max Range: 2.8683. Min Range: -2.8683

Max Act: 2.0480. Min Act: -0.0000

Data Index: 1393233 (Python Code)

Max Activating Token Index: 287

Text #17

Max Range: 2.8683. Min Range: -2.8683

Max Act: 2.0729. Min Act: -0.0000

Data Index: 1436615 (Python Code)

Max Activating Token Index: 188

Text #18

Max Range: 2.8683. Min Range: -2.8683

Max Act: 2.0466. Min Act: -0.0000

Data Index: 1556757 (Python Code)

Max Activating Token Index: 155

Text #19

Max Range: 2.8683. Min Range: -2.8683

Max Act: 2.0410. Min Act: -0.0000

Data Index: 1516902 (Python Code)

Max Activating Token Index: 190