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

Dataset: Open Web Text

Neuron 1349 in Layer 3

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: 3.9646. Min Range: -3.9646

Max Act: 3.9646. Min Act: -0.1700

Data Index: 3446810 (Open Web Text)

Max Activating Token Index: 211

Text #1

Max Range: 3.9646. Min Range: -3.9646

Max Act: 3.7963. Min Act: -0.1700

Data Index: 8567399 (Open Web Text)

Max Activating Token Index: 600

Text #2

Max Range: 3.9646. Min Range: -3.9646

Max Act: 3.7711. Min Act: -0.1700

Data Index: 5594990 (Open Web Text)

Max Activating Token Index: 705

Text #3

Max Range: 3.9646. Min Range: -3.9646

Max Act: 3.7803. Min Act: -0.1700

Data Index: 4511849 (Open Web Text)

Max Activating Token Index: 492

Text #4

Max Range: 3.9646. Min Range: -3.9646

Max Act: 3.7796. Min Act: -0.1700

Data Index: 3940841 (Open Web Text)

Max Activating Token Index: 640

Text #5

Max Range: 3.9646. Min Range: -3.9646

Max Act: 3.6625. Min Act: -0.1700

Data Index: 1325627 (Open Web Text)

Max Activating Token Index: 518

Text #6

Max Range: 3.9646. Min Range: -3.9646

Max Act: 3.7032. Min Act: -0.1700

Data Index: 524628 (Open Web Text)

Max Activating Token Index: 1018

Text #7

Max Range: 3.9646. Min Range: -3.9646

Max Act: 3.6740. Min Act: -0.1700

Data Index: 5019792 (Open Web Text)

Max Activating Token Index: 394

Text #8

Max Range: 3.9646. Min Range: -3.9646

Max Act: 3.5831. Min Act: -0.1700

Data Index: 6326840 (Open Web Text)

Max Activating Token Index: 56

Text #9

Max Range: 3.9646. Min Range: -3.9646

Max Act: 3.5991. Min Act: -0.1700

Data Index: 6936128 (Open Web Text)

Max Activating Token Index: 961

Text #10

Max Range: 3.9646. Min Range: -3.9646

Max Act: 3.5307. Min Act: -0.1700

Data Index: 6132137 (Open Web Text)

Max Activating Token Index: 179

Text #11

Max Range: 3.9646. Min Range: -3.9646

Max Act: 3.5470. Min Act: -0.1700

Data Index: 4762532 (Open Web Text)

Max Activating Token Index: 354

Text #12

Max Range: 3.9646. Min Range: -3.9646

Max Act: 3.5332. Min Act: -0.1700

Data Index: 3360477 (Open Web Text)

Max Activating Token Index: 395

Text #13

Max Range: 3.9646. Min Range: -3.9646

Max Act: 3.5062. Min Act: -0.1700

Data Index: 7676560 (Open Web Text)

Max Activating Token Index: 1006

Text #14

Max Range: 3.9646. Min Range: -3.9646

Max Act: 3.5383. Min Act: -0.1700

Data Index: 7680659 (Open Web Text)

Max Activating Token Index: 391

Text #15

Max Range: 3.9646. Min Range: -3.9646

Max Act: 3.5426. Min Act: -0.1700

Data Index: 6967073 (Open Web Text)

Max Activating Token Index: 956

Text #16

Max Range: 3.9646. Min Range: -3.9646

Max Act: 3.5598. Min Act: -0.1700

Data Index: 7148111 (Open Web Text)

Max Activating Token Index: 580

Text #17

Max Range: 3.9646. Min Range: -3.9646

Max Act: 3.5094. Min Act: -0.1700

Data Index: 2845469 (Open Web Text)

Max Activating Token Index: 762

Text #18

Max Range: 3.9646. Min Range: -3.9646

Max Act: 3.4774. Min Act: -0.1700

Data Index: 6714028 (Open Web Text)

Max Activating Token Index: 658

Text #19

Max Range: 3.9646. Min Range: -3.9646

Max Act: 3.5212. Min Act: -0.1700

Data Index: 3020442 (Open Web Text)

Max Activating Token Index: 400