Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 932 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.2519. Min Range: -3.2519

Max Act: 3.2519. Min Act: -0.1700

Data Index: 1007077 (C4 (Web Text))

Max Activating Token Index: 518

Text #1

Max Range: 3.2519. Min Range: -3.2519

Max Act: 3.2292. Min Act: -0.1700

Data Index: 1430686 (Python Code)

Max Activating Token Index: 142

Text #2

Max Range: 3.2519. Min Range: -3.2519

Max Act: 3.2329. Min Act: -0.1700

Data Index: 1555373 (Python Code)

Max Activating Token Index: 685

Text #3

Max Range: 3.2519. Min Range: -3.2519

Max Act: 3.2118. Min Act: -0.1700

Data Index: 1607699 (Python Code)

Max Activating Token Index: 182

Text #4

Max Range: 3.2519. Min Range: -3.2519

Max Act: 3.2073. Min Act: -0.1700

Data Index: 581757 (C4 (Web Text))

Max Activating Token Index: 277

Text #5

Max Range: 3.2519. Min Range: -3.2519

Max Act: 3.1901. Min Act: -0.1700

Data Index: 1435863 (Python Code)

Max Activating Token Index: 801

Text #6

Max Range: 3.2519. Min Range: -3.2519

Max Act: 3.1837. Min Act: -0.1700

Data Index: 1626260 (Python Code)

Max Activating Token Index: 350

Text #7

Max Range: 3.2519. Min Range: -3.2519

Max Act: 3.1975. Min Act: -0.1700

Data Index: 1465734 (Python Code)

Max Activating Token Index: 778

Text #8

Max Range: 3.2519. Min Range: -3.2519

Max Act: 3.1762. Min Act: -0.1700

Data Index: 1185999 (C4 (Web Text))

Max Activating Token Index: 871

Text #9

Max Range: 3.2519. Min Range: -3.2519

Max Act: 3.2167. Min Act: -0.1700

Data Index: 549936 (C4 (Web Text))

Max Activating Token Index: 552

Text #10

Max Range: 3.2519. Min Range: -3.2519

Max Act: 3.1780. Min Act: -0.1700

Data Index: 950403 (C4 (Web Text))

Max Activating Token Index: 277

Text #11

Max Range: 3.2519. Min Range: -3.2519

Max Act: 3.1785. Min Act: -0.1700

Data Index: 177636 (C4 (Web Text))

Max Activating Token Index: 716

Text #12

Max Range: 3.2519. Min Range: -3.2519

Max Act: 3.1688. Min Act: -0.1700

Data Index: 1587779 (Python Code)

Max Activating Token Index: 236

Text #13

Max Range: 3.2519. Min Range: -3.2519

Max Act: 3.1655. Min Act: -0.1700

Data Index: 1515951 (Python Code)

Max Activating Token Index: 881

Text #14

Max Range: 3.2519. Min Range: -3.2519

Max Act: 3.1784. Min Act: -0.1700

Data Index: 1589668 (Python Code)

Max Activating Token Index: 1003

Text #15

Max Range: 3.2519. Min Range: -3.2519

Max Act: 3.1639. Min Act: -0.1700

Data Index: 457212 (C4 (Web Text))

Max Activating Token Index: 505

Text #16

Max Range: 3.2519. Min Range: -3.2519

Max Act: 3.1521. Min Act: -0.1700

Data Index: 1621100 (Python Code)

Max Activating Token Index: 307

Text #17

Max Range: 3.2519. Min Range: -3.2519

Max Act: 3.1227. Min Act: -0.1700

Data Index: 1622195 (Python Code)

Max Activating Token Index: 635

Text #18

Max Range: 3.2519. Min Range: -3.2519

Max Act: 3.1258. Min Act: -0.1700

Data Index: 1531647 (Python Code)

Max Activating Token Index: 89

Text #19

Max Range: 3.2519. Min Range: -3.2519

Max Act: 3.1318. Min Act: -0.1700

Data Index: 1175446 (C4 (Web Text))

Max Activating Token Index: 279