Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 1256 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 2.2228. Min Range: -2.2228

Max Act: 2.2228. Min Act: -0.1700

Data Index: 6594291 (Open Web Text)

Max Activating Token Index: 925

Text #1

Max Range: 2.2228. Min Range: -2.2228

Max Act: 2.2123. Min Act: -0.1699

Data Index: 5638487 (Open Web Text)

Max Activating Token Index: 570

Text #2

Max Range: 2.2228. Min Range: -2.2228

Max Act: 2.1598. Min Act: -0.1700

Data Index: 6496877 (Open Web Text)

Max Activating Token Index: 581

Text #3

Max Range: 2.2228. Min Range: -2.2228

Max Act: 2.1533. Min Act: -0.1692

Data Index: 8320436 (Open Web Text)

Max Activating Token Index: 812

Text #4

Max Range: 2.2228. Min Range: -2.2228

Max Act: 2.1561. Min Act: -0.1698

Data Index: 8820565 (Open Web Text)

Max Activating Token Index: 655

Text #5

Max Range: 2.2228. Min Range: -2.2228

Max Act: 2.1430. Min Act: -0.1682

Data Index: 7095837 (Open Web Text)

Max Activating Token Index: 858

Text #6

Max Range: 2.2228. Min Range: -2.2228

Max Act: 2.1416. Min Act: -0.1700

Data Index: 4045096 (Open Web Text)

Max Activating Token Index: 323

Text #7

Max Range: 2.2228. Min Range: -2.2228

Max Act: 2.1371. Min Act: -0.1678

Data Index: 1279021 (Open Web Text)

Max Activating Token Index: 760

Text #8

Max Range: 2.2228. Min Range: -2.2228

Max Act: 2.1341. Min Act: -0.1700

Data Index: 189060 (Open Web Text)

Max Activating Token Index: 752

Text #9

Max Range: 2.2228. Min Range: -2.2228

Max Act: 2.1003. Min Act: -0.1698

Data Index: 7839585 (Open Web Text)

Max Activating Token Index: 584

Text #10

Max Range: 2.2228. Min Range: -2.2228

Max Act: 2.1222. Min Act: -0.1700

Data Index: 2068204 (Open Web Text)

Max Activating Token Index: 992

Text #11

Max Range: 2.2228. Min Range: -2.2228

Max Act: 2.0893. Min Act: -0.1697

Data Index: 4775243 (Open Web Text)

Max Activating Token Index: 776

Text #12

Max Range: 2.2228. Min Range: -2.2228

Max Act: 2.1152. Min Act: -0.1700

Data Index: 1615358 (Open Web Text)

Max Activating Token Index: 419

Text #13

Max Range: 2.2228. Min Range: -2.2228

Max Act: 2.1092. Min Act: -0.1687

Data Index: 7201689 (Open Web Text)

Max Activating Token Index: 864

Text #14

Max Range: 2.2228. Min Range: -2.2228

Max Act: 2.1202. Min Act: -0.1700

Data Index: 7484409 (Open Web Text)

Max Activating Token Index: 378

Text #15

Max Range: 2.2228. Min Range: -2.2228

Max Act: 2.0995. Min Act: -0.1700

Data Index: 6791815 (Open Web Text)

Max Activating Token Index: 979

Text #16

Max Range: 2.2228. Min Range: -2.2228

Max Act: 2.0973. Min Act: -0.1700

Data Index: 6770730 (Open Web Text)

Max Activating Token Index: 686

Text #17

Max Range: 2.2228. Min Range: -2.2228

Max Act: 2.0892. Min Act: -0.1700

Data Index: 8313590 (Open Web Text)

Max Activating Token Index: 723

Text #18

Max Range: 2.2228. Min Range: -2.2228

Max Act: 2.0782. Min Act: -0.1665

Data Index: 7674000 (Open Web Text)

Max Activating Token Index: 1021

Text #19

Max Range: 2.2228. Min Range: -2.2228

Max Act: 2.0901. Min Act: -0.1666

Data Index: 7457613 (Open Web Text)

Max Activating Token Index: 887