Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2574 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.2734. Min Range: -3.2734

Max Act: 3.2734. Min Act: -0.0000

Data Index: 1617780 (Python Code)

Max Activating Token Index: 589

Text #1

Max Range: 3.2734. Min Range: -3.2734

Max Act: 2.4464. Min Act: -0.0001

Data Index: 1636007 (Python Code)

Max Activating Token Index: 639

Text #2

Max Range: 3.2734. Min Range: -3.2734

Max Act: 2.2341. Min Act: -0.0001

Data Index: 1370713 (Python Code)

Max Activating Token Index: 157

Text #3

Max Range: 3.2734. Min Range: -3.2734

Max Act: 2.1797. Min Act: -0.0001

Data Index: 1501901 (Python Code)

Max Activating Token Index: 550

Text #4

Max Range: 3.2734. Min Range: -3.2734

Max Act: 1.9419. Min Act: -0.0001

Data Index: 1591717 (Python Code)

Max Activating Token Index: 373

Text #5

Max Range: 3.2734. Min Range: -3.2734

Max Act: 1.9284. Min Act: -0.0001

Data Index: 1468417 (Python Code)

Max Activating Token Index: 693

Text #6

Max Range: 3.2734. Min Range: -3.2734

Max Act: 1.9213. Min Act: -0.0000

Data Index: 1536549 (Python Code)

Max Activating Token Index: 282

Text #7

Max Range: 3.2734. Min Range: -3.2734

Max Act: 1.9837. Min Act: -0.0001

Data Index: 1653550 (Python Code)

Max Activating Token Index: 463

Text #8

Max Range: 3.2734. Min Range: -3.2734

Max Act: 1.9824. Min Act: -0.0000

Data Index: 1414393 (Python Code)

Max Activating Token Index: 542

Text #9

Max Range: 3.2734. Min Range: -3.2734

Max Act: 1.9312. Min Act: -0.0001

Data Index: 1520647 (Python Code)

Max Activating Token Index: 27

Text #10

Max Range: 3.2734. Min Range: -3.2734

Max Act: 1.8343. Min Act: -0.0000

Data Index: 1375893 (Python Code)

Max Activating Token Index: 669

Text #11

Max Range: 3.2734. Min Range: -3.2734

Max Act: 1.9500. Min Act: -0.0001

Data Index: 1497359 (Python Code)

Max Activating Token Index: 830

Text #12

Max Range: 3.2734. Min Range: -3.2734

Max Act: 1.7835. Min Act: -0.0001

Data Index: 1491982 (Python Code)

Max Activating Token Index: 427

Text #13

Max Range: 3.2734. Min Range: -3.2734

Max Act: 1.9015. Min Act: -0.0000

Data Index: 1595809 (Python Code)

Max Activating Token Index: 585

Text #14

Max Range: 3.2734. Min Range: -3.2734

Max Act: 1.8209. Min Act: -0.0001

Data Index: 1637528 (Python Code)

Max Activating Token Index: 902

Text #15

Max Range: 3.2734. Min Range: -3.2734

Max Act: 1.7502. Min Act: -0.0001

Data Index: 1632964 (Python Code)

Max Activating Token Index: 285

Text #16

Max Range: 3.2734. Min Range: -3.2734

Max Act: 1.7881. Min Act: -0.0001

Data Index: 1384569 (Python Code)

Max Activating Token Index: 188

Text #17

Max Range: 3.2734. Min Range: -3.2734

Max Act: 1.7250. Min Act: -0.0001

Data Index: 1499991 (Python Code)

Max Activating Token Index: 100

Text #18

Max Range: 3.2734. Min Range: -3.2734

Max Act: 1.5381. Min Act: -0.0001

Data Index: 1458815 (Python Code)

Max Activating Token Index: 760

Text #19

Max Range: 3.2734. Min Range: -3.2734

Max Act: 1.6732. Min Act: -0.0001

Data Index: 1626591 (Python Code)

Max Activating Token Index: 795