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

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

Neuron 5013 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9139. Min Range: -1.9139

Max Act: 1.9139. Min Act: -0.0000

Data Index: 1468674 (Python Code)

Max Activating Token Index: 631

Text #1

Max Range: 1.9139. Min Range: -1.9139

Max Act: 1.5514. Min Act: -0.0000

Data Index: 1470120 (Python Code)

Max Activating Token Index: 610

Text #2

Max Range: 1.9139. Min Range: -1.9139

Max Act: 1.6221. Min Act: -0.0000

Data Index: 1490520 (Python Code)

Max Activating Token Index: 413

Text #3

Max Range: 1.9139. Min Range: -1.9139

Max Act: 1.7835. Min Act: -0.0000

Data Index: 1455890 (Python Code)

Max Activating Token Index: 994

Text #4

Max Range: 1.9139. Min Range: -1.9139

Max Act: 1.6492. Min Act: -0.0000

Data Index: 33034 (C4 (Web Text))

Max Activating Token Index: 519

Text #5

Max Range: 1.9139. Min Range: -1.9139

Max Act: 1.6170. Min Act: -0.0000

Data Index: 1580246 (Python Code)

Max Activating Token Index: 419

Text #6

Max Range: 1.9139. Min Range: -1.9139

Max Act: 1.5443. Min Act: -0.0000

Data Index: 1447977 (Python Code)

Max Activating Token Index: 114

Text #7

Max Range: 1.9139. Min Range: -1.9139

Max Act: 1.4586. Min Act: -0.0000

Data Index: 1562020 (Python Code)

Max Activating Token Index: 521

Text #8

Max Range: 1.9139. Min Range: -1.9139

Max Act: 1.5734. Min Act: -0.0000

Data Index: 1571668 (Python Code)

Max Activating Token Index: 451

Text #9

Max Range: 1.9139. Min Range: -1.9139

Max Act: 1.5378. Min Act: -0.0000

Data Index: 1559002 (Python Code)

Max Activating Token Index: 441

Text #10

Max Range: 1.9139. Min Range: -1.9139

Max Act: 1.4263. Min Act: -0.0000

Data Index: 1587968 (Python Code)

Max Activating Token Index: 356

Text #11

Max Range: 1.9139. Min Range: -1.9139

Max Act: 1.3811. Min Act: -0.0000

Data Index: 1396941 (Python Code)

Max Activating Token Index: 175

Text #12

Max Range: 1.9139. Min Range: -1.9139

Max Act: 1.5284. Min Act: -0.0000

Data Index: 1419243 (Python Code)

Max Activating Token Index: 733

Text #13

Max Range: 1.9139. Min Range: -1.9139

Max Act: 1.1879. Min Act: -0.0000

Data Index: 1500289 (Python Code)

Max Activating Token Index: 194

Text #14

Max Range: 1.9139. Min Range: -1.9139

Max Act: 1.3199. Min Act: -0.0000

Data Index: 1524934 (Python Code)

Max Activating Token Index: 796

Text #15

Max Range: 1.9139. Min Range: -1.9139

Max Act: 1.5370. Min Act: -0.0000

Data Index: 1547024 (Python Code)

Max Activating Token Index: 775

Text #16

Max Range: 1.9139. Min Range: -1.9139

Max Act: 1.3885. Min Act: -0.0000

Data Index: 1566900 (Python Code)

Max Activating Token Index: 793

Text #17

Max Range: 1.9139. Min Range: -1.9139

Max Act: 1.2812. Min Act: -0.0000

Data Index: 1646389 (Python Code)

Max Activating Token Index: 125

Text #18

Max Range: 1.9139. Min Range: -1.9139

Max Act: 1.2440. Min Act: -0.0000

Data Index: 1570725 (Python Code)

Max Activating Token Index: 371

Text #19

Max Range: 1.9139. Min Range: -1.9139

Max Act: 1.3228. Min Act: -0.0000

Data Index: 1589082 (Python Code)

Max Activating Token Index: 660