Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 923 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.8769. Min Range: -5.8769

Max Act: 5.8769. Min Act: -0.1700

Data Index: 1620626 (Python Code)

Max Activating Token Index: 649

Text #1

Max Range: 5.8769. Min Range: -5.8769

Max Act: 5.7831. Min Act: -0.1700

Data Index: 1365465 (Python Code)

Max Activating Token Index: 476

Text #2

Max Range: 5.8769. Min Range: -5.8769

Max Act: 5.6894. Min Act: -0.1700

Data Index: 1526033 (Python Code)

Max Activating Token Index: 52

Text #3

Max Range: 5.8769. Min Range: -5.8769

Max Act: 5.7206. Min Act: -0.1700

Data Index: 1383827 (Python Code)

Max Activating Token Index: 330

Text #4

Max Range: 5.8769. Min Range: -5.8769

Max Act: 5.6894. Min Act: -0.1700

Data Index: 1507226 (Python Code)

Max Activating Token Index: 157

Text #5

Max Range: 5.8769. Min Range: -5.8769

Max Act: 5.6269. Min Act: -0.1700

Data Index: 1612644 (Python Code)

Max Activating Token Index: 123

Text #6

Max Range: 5.8769. Min Range: -5.8769

Max Act: 5.6581. Min Act: -0.1700

Data Index: 1619136 (Python Code)

Max Activating Token Index: 451

Text #7

Max Range: 5.8769. Min Range: -5.8769

Max Act: 5.6269. Min Act: -0.1700

Data Index: 1507598 (Python Code)

Max Activating Token Index: 785

Text #8

Max Range: 5.8769. Min Range: -5.8769

Max Act: 5.5331. Min Act: -0.1700

Data Index: 1552493 (Python Code)

Max Activating Token Index: 77

Text #9

Max Range: 5.8769. Min Range: -5.8769

Max Act: 5.5331. Min Act: -0.1700

Data Index: 1592526 (Python Code)

Max Activating Token Index: 141

Text #10

Max Range: 5.8769. Min Range: -5.8769

Max Act: 5.5644. Min Act: -0.1700

Data Index: 1406721 (Python Code)

Max Activating Token Index: 493

Text #11

Max Range: 5.8769. Min Range: -5.8769

Max Act: 5.5019. Min Act: -0.1700

Data Index: 1460930 (Python Code)

Max Activating Token Index: 442

Text #12

Max Range: 5.8769. Min Range: -5.8769

Max Act: 5.5019. Min Act: -0.1700

Data Index: 1528390 (Python Code)

Max Activating Token Index: 213

Text #13

Max Range: 5.8769. Min Range: -5.8769

Max Act: 5.5644. Min Act: -0.1700

Data Index: 1411709 (Python Code)

Max Activating Token Index: 244

Text #14

Max Range: 5.8769. Min Range: -5.8769

Max Act: 5.5956. Min Act: -0.1700

Data Index: 1503567 (Python Code)

Max Activating Token Index: 475

Text #15

Max Range: 5.8769. Min Range: -5.8769

Max Act: 5.5019. Min Act: -0.1700

Data Index: 1380931 (Python Code)

Max Activating Token Index: 32

Text #16

Max Range: 5.8769. Min Range: -5.8769

Max Act: 5.4394. Min Act: -0.1700

Data Index: 1489884 (Python Code)

Max Activating Token Index: 365

Text #17

Max Range: 5.8769. Min Range: -5.8769

Max Act: 5.5019. Min Act: -0.1700

Data Index: 1395547 (Python Code)

Max Activating Token Index: 553

Text #18

Max Range: 5.8769. Min Range: -5.8769

Max Act: 5.5019. Min Act: -0.1700

Data Index: 1497550 (Python Code)

Max Activating Token Index: 172

Text #19

Max Range: 5.8769. Min Range: -5.8769

Max Act: 5.4706. Min Act: -0.1700

Data Index: 1438130 (Python Code)

Max Activating Token Index: 395