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

Dataset: Open Web Text

Neuron 2026 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: 6.0311. Min Range: -6.0311

Max Act: 5.9800. Min Act: -0.1700

Data Index: 860001 (Open Web Text)

Max Activating Token Index: 270

Text #1

Max Range: 6.0311. Min Range: -6.0311

Max Act: 6.0311. Min Act: -0.1697

Data Index: 7836356 (Open Web Text)

Max Activating Token Index: 831

Text #2

Max Range: 6.0311. Min Range: -6.0311

Max Act: 5.9563. Min Act: -0.1700

Data Index: 8812256 (Open Web Text)

Max Activating Token Index: 477

Text #3

Max Range: 6.0311. Min Range: -6.0311

Max Act: 5.8822. Min Act: -0.1700

Data Index: 650485 (Open Web Text)

Max Activating Token Index: 78

Text #4

Max Range: 6.0311. Min Range: -6.0311

Max Act: 5.8183. Min Act: -0.1700

Data Index: 8249983 (Open Web Text)

Max Activating Token Index: 415

Text #5

Max Range: 6.0311. Min Range: -6.0311

Max Act: 5.7231. Min Act: -0.1700

Data Index: 5926744 (Open Web Text)

Max Activating Token Index: 457

Text #6

Max Range: 6.0311. Min Range: -6.0311

Max Act: 5.7127. Min Act: -0.1700

Data Index: 2139120 (Open Web Text)

Max Activating Token Index: 908

Text #7

Max Range: 6.0311. Min Range: -6.0311

Max Act: 5.7073. Min Act: -0.1700

Data Index: 8024155 (Open Web Text)

Max Activating Token Index: 1013

Text #8

Max Range: 6.0311. Min Range: -6.0311

Max Act: 5.7076. Min Act: -0.1700

Data Index: 6738599 (Open Web Text)

Max Activating Token Index: 790

Text #9

Max Range: 6.0311. Min Range: -6.0311

Max Act: 5.6125. Min Act: -0.1700

Data Index: 6149047 (Open Web Text)

Max Activating Token Index: 917

Text #10

Max Range: 6.0311. Min Range: -6.0311

Max Act: 5.6749. Min Act: -0.1700

Data Index: 7175995 (Open Web Text)

Max Activating Token Index: 363

Text #11

Max Range: 6.0311. Min Range: -6.0311

Max Act: 5.6585. Min Act: -0.1700

Data Index: 2164046 (Open Web Text)

Max Activating Token Index: 122

Text #12

Max Range: 6.0311. Min Range: -6.0311

Max Act: 5.6771. Min Act: -0.1700

Data Index: 111868 (Open Web Text)

Max Activating Token Index: 611

Text #13

Max Range: 6.0311. Min Range: -6.0311

Max Act: 5.6047. Min Act: -0.1700

Data Index: 21075 (Open Web Text)

Max Activating Token Index: 204

Text #14

Max Range: 6.0311. Min Range: -6.0311

Max Act: 5.6459. Min Act: -0.1695

Data Index: 4030662 (Open Web Text)

Max Activating Token Index: 1002

Text #15

Max Range: 6.0311. Min Range: -6.0311

Max Act: 5.6008. Min Act: -0.1700

Data Index: 1759606 (Open Web Text)

Max Activating Token Index: 788

Text #16

Max Range: 6.0311. Min Range: -6.0311

Max Act: 5.5920. Min Act: -0.1700

Data Index: 2329001 (Open Web Text)

Max Activating Token Index: 978

Text #17

Max Range: 6.0311. Min Range: -6.0311

Max Act: 5.5695. Min Act: -0.1700

Data Index: 4580242 (Open Web Text)

Max Activating Token Index: 96

Text #18

Max Range: 6.0311. Min Range: -6.0311

Max Act: 5.5783. Min Act: -0.1700

Data Index: 2399161 (Open Web Text)

Max Activating Token Index: 726

Text #19

Max Range: 6.0311. Min Range: -6.0311

Max Act: 5.6322. Min Act: -0.1700

Data Index: 3287949 (Open Web Text)

Max Activating Token Index: 408