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

Dataset: Open Web Text

Neuron 788 in Layer 2

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: 3.8123. Min Range: -3.8123

Max Act: 3.8123. Min Act: -0.1700

Data Index: 4793081 (Open Web Text)

Max Activating Token Index: 85

Text #1

Max Range: 3.8123. Min Range: -3.8123

Max Act: 3.7618. Min Act: -0.1700

Data Index: 3098328 (Open Web Text)

Max Activating Token Index: 343

Text #2

Max Range: 3.8123. Min Range: -3.8123

Max Act: 3.7196. Min Act: -0.1700

Data Index: 6564311 (Open Web Text)

Max Activating Token Index: 390

Text #3

Max Range: 3.8123. Min Range: -3.8123

Max Act: 3.7259. Min Act: -0.1700

Data Index: 701109 (Open Web Text)

Max Activating Token Index: 148

Text #4

Max Range: 3.8123. Min Range: -3.8123

Max Act: 3.7044. Min Act: -0.1700

Data Index: 8179712 (Open Web Text)

Max Activating Token Index: 83

Text #5

Max Range: 3.8123. Min Range: -3.8123

Max Act: 3.6440. Min Act: -0.1700

Data Index: 159749 (Open Web Text)

Max Activating Token Index: 840

Text #6

Max Range: 3.8123. Min Range: -3.8123

Max Act: 3.6990. Min Act: -0.1700

Data Index: 1351528 (Open Web Text)

Max Activating Token Index: 222

Text #7

Max Range: 3.8123. Min Range: -3.8123

Max Act: 3.6898. Min Act: -0.1700

Data Index: 5007505 (Open Web Text)

Max Activating Token Index: 358

Text #8

Max Range: 3.8123. Min Range: -3.8123

Max Act: 3.6249. Min Act: -0.1700

Data Index: 4455178 (Open Web Text)

Max Activating Token Index: 860

Text #9

Max Range: 3.8123. Min Range: -3.8123

Max Act: 3.6937. Min Act: -0.1700

Data Index: 2160227 (Open Web Text)

Max Activating Token Index: 533

Text #10

Max Range: 3.8123. Min Range: -3.8123

Max Act: 3.6820. Min Act: -0.1700

Data Index: 1008333 (Open Web Text)

Max Activating Token Index: 119

Text #11

Max Range: 3.8123. Min Range: -3.8123

Max Act: 3.6342. Min Act: -0.1700

Data Index: 7008501 (Open Web Text)

Max Activating Token Index: 263

Text #12

Max Range: 3.8123. Min Range: -3.8123

Max Act: 3.6430. Min Act: -0.1700

Data Index: 1918597 (Open Web Text)

Max Activating Token Index: 391

Text #13

Max Range: 3.8123. Min Range: -3.8123

Max Act: 3.6782. Min Act: -0.1700

Data Index: 7643025 (Open Web Text)

Max Activating Token Index: 218

Text #14

Max Range: 3.8123. Min Range: -3.8123

Max Act: 3.6226. Min Act: -0.1700

Data Index: 7793104 (Open Web Text)

Max Activating Token Index: 513

Text #15

Max Range: 3.8123. Min Range: -3.8123

Max Act: 3.6479. Min Act: -0.1700

Data Index: 1214306 (Open Web Text)

Max Activating Token Index: 403

Text #16

Max Range: 3.8123. Min Range: -3.8123

Max Act: 3.6874. Min Act: -0.1700

Data Index: 2290079 (Open Web Text)

Max Activating Token Index: 452

Text #17

Max Range: 3.8123. Min Range: -3.8123

Max Act: 3.6475. Min Act: -0.1700

Data Index: 6903254 (Open Web Text)

Max Activating Token Index: 179

Text #18

Max Range: 3.8123. Min Range: -3.8123

Max Act: 3.6301. Min Act: -0.1700

Data Index: 784603 (Open Web Text)

Max Activating Token Index: 532

Text #19

Max Range: 3.8123. Min Range: -3.8123

Max Act: 3.6742. Min Act: -0.1700

Data Index: 1463013 (Open Web Text)

Max Activating Token Index: 38