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

Dataset: Open Web Text

Neuron 921 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: 3.1845. Min Range: -3.1845

Max Act: 3.1845. Min Act: -0.1700

Data Index: 5779294 (Open Web Text)

Max Activating Token Index: 995

Text #1

Max Range: 3.1845. Min Range: -3.1845

Max Act: 3.0307. Min Act: -0.1700

Data Index: 7330602 (Open Web Text)

Max Activating Token Index: 137

Text #2

Max Range: 3.1845. Min Range: -3.1845

Max Act: 3.0120. Min Act: -0.1700

Data Index: 8218002 (Open Web Text)

Max Activating Token Index: 435

Text #3

Max Range: 3.1845. Min Range: -3.1845

Max Act: 3.0076. Min Act: -0.1700

Data Index: 1796329 (Open Web Text)

Max Activating Token Index: 400

Text #4

Max Range: 3.1845. Min Range: -3.1845

Max Act: 2.9403. Min Act: -0.1700

Data Index: 391422 (Open Web Text)

Max Activating Token Index: 343

Text #5

Max Range: 3.1845. Min Range: -3.1845

Max Act: 2.9593. Min Act: -0.1700

Data Index: 3659509 (Open Web Text)

Max Activating Token Index: 869

Text #6

Max Range: 3.1845. Min Range: -3.1845

Max Act: 2.9010. Min Act: -0.1700

Data Index: 1538905 (Open Web Text)

Max Activating Token Index: 968

Text #7

Max Range: 3.1845. Min Range: -3.1845

Max Act: 2.9001. Min Act: -0.1700

Data Index: 8126924 (Open Web Text)

Max Activating Token Index: 905

Text #8

Max Range: 3.1845. Min Range: -3.1845

Max Act: 2.9087. Min Act: -0.1700

Data Index: 3098135 (Open Web Text)

Max Activating Token Index: 609

Text #9

Max Range: 3.1845. Min Range: -3.1845

Max Act: 2.9137. Min Act: -0.1700

Data Index: 8430467 (Open Web Text)

Max Activating Token Index: 202

Text #10

Max Range: 3.1845. Min Range: -3.1845

Max Act: 2.8789. Min Act: -0.1700

Data Index: 414835 (Open Web Text)

Max Activating Token Index: 219

Text #11

Max Range: 3.1845. Min Range: -3.1845

Max Act: 2.8803. Min Act: -0.1700

Data Index: 56866 (Open Web Text)

Max Activating Token Index: 161

Text #12

Max Range: 3.1845. Min Range: -3.1845

Max Act: 2.8822. Min Act: -0.1700

Data Index: 5563029 (Open Web Text)

Max Activating Token Index: 545

Text #13

Max Range: 3.1845. Min Range: -3.1845

Max Act: 2.8841. Min Act: -0.1700

Data Index: 2955920 (Open Web Text)

Max Activating Token Index: 951

Text #14

Max Range: 3.1845. Min Range: -3.1845

Max Act: 2.8794. Min Act: -0.1700

Data Index: 5711935 (Open Web Text)

Max Activating Token Index: 291

Text #15

Max Range: 3.1845. Min Range: -3.1845

Max Act: 2.8961. Min Act: -0.1700

Data Index: 3898577 (Open Web Text)

Max Activating Token Index: 347

Text #16

Max Range: 3.1845. Min Range: -3.1845

Max Act: 2.8690. Min Act: -0.1700

Data Index: 8324798 (Open Web Text)

Max Activating Token Index: 118

Text #17

Max Range: 3.1845. Min Range: -3.1845

Max Act: 2.8542. Min Act: -0.1700

Data Index: 78244 (Open Web Text)

Max Activating Token Index: 975

Text #18

Max Range: 3.1845. Min Range: -3.1845

Max Act: 2.8284. Min Act: -0.1700

Data Index: 7352824 (Open Web Text)

Max Activating Token Index: 240

Text #19

Max Range: 3.1845. Min Range: -3.1845

Max Act: 2.8301. Min Act: -0.1700

Data Index: 878677 (Open Web Text)

Max Activating Token Index: 557