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

Dataset: Open Web Text

Neuron 2920 in Layer 0

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: 6.1561. Min Range: -6.1561

Max Act: 6.1561. Min Act: -0.1700

Data Index: 5036174 (Open Web Text)

Max Activating Token Index: 16

Text #1

Max Range: 6.1561. Min Range: -6.1561

Max Act: 5.8778. Min Act: -0.1693

Data Index: 7745330 (Open Web Text)

Max Activating Token Index: 554

Text #2

Max Range: 6.1561. Min Range: -6.1561

Max Act: 5.8926. Min Act: -0.1690

Data Index: 5645723 (Open Web Text)

Max Activating Token Index: 32

Text #3

Max Range: 6.1561. Min Range: -6.1561

Max Act: 5.8189. Min Act: -0.1700

Data Index: 842705 (Open Web Text)

Max Activating Token Index: 35

Text #4

Max Range: 6.1561. Min Range: -6.1561

Max Act: 5.7981. Min Act: -0.1699

Data Index: 7745333 (Open Web Text)

Max Activating Token Index: 543

Text #5

Max Range: 6.1561. Min Range: -6.1561

Max Act: 5.8137. Min Act: -0.1700

Data Index: 8131022 (Open Web Text)

Max Activating Token Index: 52

Text #6

Max Range: 6.1561. Min Range: -6.1561

Max Act: 5.7445. Min Act: -0.1622

Data Index: 2822526 (Open Web Text)

Max Activating Token Index: 156

Text #7

Max Range: 6.1561. Min Range: -6.1561

Max Act: 5.7021. Min Act: -0.1685

Data Index: 3136888 (Open Web Text)

Max Activating Token Index: 501

Text #8

Max Range: 6.1561. Min Range: -6.1561

Max Act: 5.7052. Min Act: -0.1598

Data Index: 7745331 (Open Web Text)

Max Activating Token Index: 669

Text #9

Max Range: 6.1561. Min Range: -6.1561

Max Act: 5.6257. Min Act: -0.1638

Data Index: 3136887 (Open Web Text)

Max Activating Token Index: 797

Text #10

Max Range: 6.1561. Min Range: -6.1561

Max Act: 5.6435. Min Act: -0.1699

Data Index: 8469870 (Open Web Text)

Max Activating Token Index: 984

Text #11

Max Range: 6.1561. Min Range: -6.1561

Max Act: 5.5807. Min Act: -0.0869

Data Index: 7745329 (Open Web Text)

Max Activating Token Index: 1005

Text #12

Max Range: 6.1561. Min Range: -6.1561

Max Act: 5.5805. Min Act: -0.1697

Data Index: 8469859 (Open Web Text)

Max Activating Token Index: 493

Text #13

Max Range: 6.1561. Min Range: -6.1561

Max Act: 5.5757. Min Act: -0.1649

Data Index: 8131028 (Open Web Text)

Max Activating Token Index: 947

Text #14

Max Range: 6.1561. Min Range: -6.1561

Max Act: 5.5759. Min Act: -0.1616

Data Index: 5865760 (Open Web Text)

Max Activating Token Index: 33

Text #15

Max Range: 6.1561. Min Range: -6.1561

Max Act: 5.5656. Min Act: -0.1307

Data Index: 8216402 (Open Web Text)

Max Activating Token Index: 110

Text #16

Max Range: 6.1561. Min Range: -6.1561

Max Act: 5.5331. Min Act: -0.1699

Data Index: 8131026 (Open Web Text)

Max Activating Token Index: 910

Text #17

Max Range: 6.1561. Min Range: -6.1561

Max Act: 5.5278. Min Act: -0.1442

Data Index: 8201185 (Open Web Text)

Max Activating Token Index: 562

Text #18

Max Range: 6.1561. Min Range: -6.1561

Max Act: 5.5364. Min Act: -0.1691

Data Index: 3069787 (Open Web Text)

Max Activating Token Index: 634

Text #19

Max Range: 6.1561. Min Range: -6.1561

Max Act: 5.5288. Min Act: -0.1695

Data Index: 1760762 (Open Web Text)

Max Activating Token Index: 76