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

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

Neuron 1951 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: 4.3923. Min Range: -4.3923

Max Act: 4.3923. Min Act: -0.1700

Data Index: 491649 (C4 (Web Text))

Max Activating Token Index: 284

Text #1

Max Range: 4.3923. Min Range: -4.3923

Max Act: 4.3238. Min Act: -0.1700

Data Index: 883350 (C4 (Web Text))

Max Activating Token Index: 497

Text #2

Max Range: 4.3923. Min Range: -4.3923

Max Act: 4.2342. Min Act: -0.1700

Data Index: 849112 (C4 (Web Text))

Max Activating Token Index: 882

Text #3

Max Range: 4.3923. Min Range: -4.3923

Max Act: 4.2636. Min Act: -0.1700

Data Index: 1347782 (C4 (Web Text))

Max Activating Token Index: 746

Text #4

Max Range: 4.3923. Min Range: -4.3923

Max Act: 4.2079. Min Act: -0.1700

Data Index: 163075 (C4 (Web Text))

Max Activating Token Index: 693

Text #5

Max Range: 4.3923. Min Range: -4.3923

Max Act: 4.1838. Min Act: -0.1700

Data Index: 1265070 (C4 (Web Text))

Max Activating Token Index: 847

Text #6

Max Range: 4.3923. Min Range: -4.3923

Max Act: 4.1785. Min Act: -0.1700

Data Index: 780760 (C4 (Web Text))

Max Activating Token Index: 674

Text #7

Max Range: 4.3923. Min Range: -4.3923

Max Act: 4.1926. Min Act: -0.1700

Data Index: 1224272 (C4 (Web Text))

Max Activating Token Index: 738

Text #8

Max Range: 4.3923. Min Range: -4.3923

Max Act: 4.1805. Min Act: -0.1700

Data Index: 1118573 (C4 (Web Text))

Max Activating Token Index: 239

Text #9

Max Range: 4.3923. Min Range: -4.3923

Max Act: 4.1617. Min Act: -0.1700

Data Index: 958438 (C4 (Web Text))

Max Activating Token Index: 842

Text #10

Max Range: 4.3923. Min Range: -4.3923

Max Act: 4.1775. Min Act: -0.1700

Data Index: 1208873 (C4 (Web Text))

Max Activating Token Index: 899

Text #11

Max Range: 4.3923. Min Range: -4.3923

Max Act: 4.1681. Min Act: -0.1700

Data Index: 1251973 (C4 (Web Text))

Max Activating Token Index: 634

Text #12

Max Range: 4.3923. Min Range: -4.3923

Max Act: 4.1381. Min Act: -0.1700

Data Index: 1194782 (C4 (Web Text))

Max Activating Token Index: 494

Text #13

Max Range: 4.3923. Min Range: -4.3923

Max Act: 4.1785. Min Act: -0.1700

Data Index: 1326651 (C4 (Web Text))

Max Activating Token Index: 602

Text #14

Max Range: 4.3923. Min Range: -4.3923

Max Act: 4.1503. Min Act: -0.1700

Data Index: 1038899 (C4 (Web Text))

Max Activating Token Index: 720

Text #15

Max Range: 4.3923. Min Range: -4.3923

Max Act: 4.1741. Min Act: -0.1700

Data Index: 1263620 (C4 (Web Text))

Max Activating Token Index: 860

Text #16

Max Range: 4.3923. Min Range: -4.3923

Max Act: 4.1697. Min Act: -0.1700

Data Index: 970929 (C4 (Web Text))

Max Activating Token Index: 657

Text #17

Max Range: 4.3923. Min Range: -4.3923

Max Act: 4.1346. Min Act: -0.1700

Data Index: 549859 (C4 (Web Text))

Max Activating Token Index: 874

Text #18

Max Range: 4.3923. Min Range: -4.3923

Max Act: 4.1505. Min Act: -0.1700

Data Index: 1107988 (C4 (Web Text))

Max Activating Token Index: 732

Text #19

Max Range: 4.3923. Min Range: -4.3923

Max Act: 4.1371. Min Act: -0.1700

Data Index: 1322914 (C4 (Web Text))

Max Activating Token Index: 679