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

Dataset: Open Web Text

Neuron 627 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: 4.7699. Min Range: -4.7699

Max Act: 4.7699. Min Act: -0.1700

Data Index: 30230 (Open Web Text)

Max Activating Token Index: 616

Text #1

Max Range: 4.7699. Min Range: -4.7699

Max Act: 4.7346. Min Act: -0.1700

Data Index: 8538990 (Open Web Text)

Max Activating Token Index: 517

Text #2

Max Range: 4.7699. Min Range: -4.7699

Max Act: 4.7180. Min Act: -0.1700

Data Index: 2292229 (Open Web Text)

Max Activating Token Index: 555

Text #3

Max Range: 4.7699. Min Range: -4.7699

Max Act: 4.6656. Min Act: -0.1700

Data Index: 4073796 (Open Web Text)

Max Activating Token Index: 510

Text #4

Max Range: 4.7699. Min Range: -4.7699

Max Act: 4.6795. Min Act: -0.1700

Data Index: 7904234 (Open Web Text)

Max Activating Token Index: 848

Text #5

Max Range: 4.7699. Min Range: -4.7699

Max Act: 4.7029. Min Act: -0.1700

Data Index: 7798757 (Open Web Text)

Max Activating Token Index: 290

Text #6

Max Range: 4.7699. Min Range: -4.7699

Max Act: 4.7100. Min Act: -0.1700

Data Index: 3336814 (Open Web Text)

Max Activating Token Index: 718

Text #7

Max Range: 4.7699. Min Range: -4.7699

Max Act: 4.6486. Min Act: -0.1700

Data Index: 4475288 (Open Web Text)

Max Activating Token Index: 641

Text #8

Max Range: 4.7699. Min Range: -4.7699

Max Act: 4.6366. Min Act: -0.1700

Data Index: 7917973 (Open Web Text)

Max Activating Token Index: 117

Text #9

Max Range: 4.7699. Min Range: -4.7699

Max Act: 4.6688. Min Act: -0.1700

Data Index: 6475187 (Open Web Text)

Max Activating Token Index: 294

Text #10

Max Range: 4.7699. Min Range: -4.7699

Max Act: 4.6337. Min Act: -0.1700

Data Index: 2963848 (Open Web Text)

Max Activating Token Index: 166

Text #11

Max Range: 4.7699. Min Range: -4.7699

Max Act: 4.6365. Min Act: -0.1700

Data Index: 5718855 (Open Web Text)

Max Activating Token Index: 673

Text #12

Max Range: 4.7699. Min Range: -4.7699

Max Act: 4.6385. Min Act: -0.1700

Data Index: 3114609 (Open Web Text)

Max Activating Token Index: 841

Text #13

Max Range: 4.7699. Min Range: -4.7699

Max Act: 4.6481. Min Act: -0.1700

Data Index: 2708732 (Open Web Text)

Max Activating Token Index: 496

Text #14

Max Range: 4.7699. Min Range: -4.7699

Max Act: 4.5965. Min Act: -0.1700

Data Index: 1712652 (Open Web Text)

Max Activating Token Index: 454

Text #15

Max Range: 4.7699. Min Range: -4.7699

Max Act: 4.6319. Min Act: -0.1700

Data Index: 3656431 (Open Web Text)

Max Activating Token Index: 200

Text #16

Max Range: 4.7699. Min Range: -4.7699

Max Act: 4.6206. Min Act: -0.1700

Data Index: 7297877 (Open Web Text)

Max Activating Token Index: 238

Text #17

Max Range: 4.7699. Min Range: -4.7699

Max Act: 4.6090. Min Act: -0.1700

Data Index: 5587986 (Open Web Text)

Max Activating Token Index: 871

Text #18

Max Range: 4.7699. Min Range: -4.7699

Max Act: 4.6192. Min Act: -0.1700

Data Index: 1186673 (Open Web Text)

Max Activating Token Index: 195

Text #19

Max Range: 4.7699. Min Range: -4.7699

Max Act: 4.6259. Min Act: -0.1700

Data Index: 5486041 (Open Web Text)

Max Activating Token Index: 723