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

Dataset: Open Web Text

Neuron 794 in Layer 5

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: 3.4090. Min Range: -3.4090

Max Act: 3.4090. Min Act: -0.1700

Data Index: 1860893 (Open Web Text)

Max Activating Token Index: 912

Text #1

Max Range: 3.4090. Min Range: -3.4090

Max Act: 3.3161. Min Act: -0.1700

Data Index: 1702945 (Open Web Text)

Max Activating Token Index: 923

Text #2

Max Range: 3.4090. Min Range: -3.4090

Max Act: 3.2823. Min Act: -0.1700

Data Index: 217764 (Open Web Text)

Max Activating Token Index: 352

Text #3

Max Range: 3.4090. Min Range: -3.4090

Max Act: 3.2194. Min Act: -0.1700

Data Index: 4098960 (Open Web Text)

Max Activating Token Index: 891

Text #4

Max Range: 3.4090. Min Range: -3.4090

Max Act: 3.2162. Min Act: -0.1700

Data Index: 3513066 (Open Web Text)

Max Activating Token Index: 511

Text #5

Max Range: 3.4090. Min Range: -3.4090

Max Act: 3.2133. Min Act: -0.1700

Data Index: 1071136 (Open Web Text)

Max Activating Token Index: 752

Text #6

Max Range: 3.4090. Min Range: -3.4090

Max Act: 3.1954. Min Act: -0.1700

Data Index: 5820984 (Open Web Text)

Max Activating Token Index: 816

Text #7

Max Range: 3.4090. Min Range: -3.4090

Max Act: 3.1900. Min Act: -0.1700

Data Index: 6244847 (Open Web Text)

Max Activating Token Index: 1015

Text #8

Max Range: 3.4090. Min Range: -3.4090

Max Act: 3.1846. Min Act: -0.1700

Data Index: 3182944 (Open Web Text)

Max Activating Token Index: 411

Text #9

Max Range: 3.4090. Min Range: -3.4090

Max Act: 3.1813. Min Act: -0.1700

Data Index: 8555878 (Open Web Text)

Max Activating Token Index: 680

Text #10

Max Range: 3.4090. Min Range: -3.4090

Max Act: 3.1845. Min Act: -0.1700

Data Index: 3985249 (Open Web Text)

Max Activating Token Index: 906

Text #11

Max Range: 3.4090. Min Range: -3.4090

Max Act: 3.1783. Min Act: -0.1700

Data Index: 3474675 (Open Web Text)

Max Activating Token Index: 674

Text #12

Max Range: 3.4090. Min Range: -3.4090

Max Act: 3.1668. Min Act: -0.1700

Data Index: 814854 (Open Web Text)

Max Activating Token Index: 341

Text #13

Max Range: 3.4090. Min Range: -3.4090

Max Act: 3.1564. Min Act: -0.1700

Data Index: 6802533 (Open Web Text)

Max Activating Token Index: 226

Text #14

Max Range: 3.4090. Min Range: -3.4090

Max Act: 3.1806. Min Act: -0.1700

Data Index: 4195735 (Open Web Text)

Max Activating Token Index: 849

Text #15

Max Range: 3.4090. Min Range: -3.4090

Max Act: 3.1691. Min Act: -0.1700

Data Index: 1646486 (Open Web Text)

Max Activating Token Index: 441

Text #16

Max Range: 3.4090. Min Range: -3.4090

Max Act: 3.1613. Min Act: -0.1700

Data Index: 4781857 (Open Web Text)

Max Activating Token Index: 840

Text #17

Max Range: 3.4090. Min Range: -3.4090

Max Act: 3.1337. Min Act: -0.1700

Data Index: 5872013 (Open Web Text)

Max Activating Token Index: 653

Text #18

Max Range: 3.4090. Min Range: -3.4090

Max Act: 3.1124. Min Act: -0.1700

Data Index: 6293054 (Open Web Text)

Max Activating Token Index: 303

Text #19

Max Range: 3.4090. Min Range: -3.4090

Max Act: 3.1023. Min Act: -0.1700

Data Index: 3391430 (Open Web Text)

Max Activating Token Index: 830