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

Dataset: Open Web Text

Neuron 1315 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: 4.0846. Min Range: -4.0846

Max Act: 4.0846. Min Act: -0.1700

Data Index: 3918701 (Open Web Text)

Max Activating Token Index: 421

Text #1

Max Range: 4.0846. Min Range: -4.0846

Max Act: 3.8989. Min Act: -0.1700

Data Index: 6391600 (Open Web Text)

Max Activating Token Index: 594

Text #2

Max Range: 4.0846. Min Range: -4.0846

Max Act: 4.0206. Min Act: -0.1700

Data Index: 5790539 (Open Web Text)

Max Activating Token Index: 465

Text #3

Max Range: 4.0846. Min Range: -4.0846

Max Act: 3.9027. Min Act: -0.1700

Data Index: 1072585 (Open Web Text)

Max Activating Token Index: 630

Text #4

Max Range: 4.0846. Min Range: -4.0846

Max Act: 3.9207. Min Act: -0.1700

Data Index: 2796907 (Open Web Text)

Max Activating Token Index: 667

Text #5

Max Range: 4.0846. Min Range: -4.0846

Max Act: 3.8953. Min Act: -0.1700

Data Index: 4119329 (Open Web Text)

Max Activating Token Index: 781

Text #6

Max Range: 4.0846. Min Range: -4.0846

Max Act: 3.9127. Min Act: -0.1700

Data Index: 1347508 (Open Web Text)

Max Activating Token Index: 918

Text #7

Max Range: 4.0846. Min Range: -4.0846

Max Act: 3.8856. Min Act: -0.1700

Data Index: 8095887 (Open Web Text)

Max Activating Token Index: 426

Text #8

Max Range: 4.0846. Min Range: -4.0846

Max Act: 3.8627. Min Act: -0.1700

Data Index: 1398405 (Open Web Text)

Max Activating Token Index: 881

Text #9

Max Range: 4.0846. Min Range: -4.0846

Max Act: 3.7926. Min Act: -0.1700

Data Index: 3543833 (Open Web Text)

Max Activating Token Index: 375

Text #10

Max Range: 4.0846. Min Range: -4.0846

Max Act: 3.8370. Min Act: -0.1700

Data Index: 7067568 (Open Web Text)

Max Activating Token Index: 693

Text #11

Max Range: 4.0846. Min Range: -4.0846

Max Act: 3.8471. Min Act: -0.1700

Data Index: 2471779 (Open Web Text)

Max Activating Token Index: 91

Text #12

Max Range: 4.0846. Min Range: -4.0846

Max Act: 3.7736. Min Act: -0.1700

Data Index: 3646449 (Open Web Text)

Max Activating Token Index: 467

Text #13

Max Range: 4.0846. Min Range: -4.0846

Max Act: 3.7327. Min Act: -0.1700

Data Index: 2578645 (Open Web Text)

Max Activating Token Index: 778

Text #14

Max Range: 4.0846. Min Range: -4.0846

Max Act: 3.7573. Min Act: -0.1700

Data Index: 3288392 (Open Web Text)

Max Activating Token Index: 236

Text #15

Max Range: 4.0846. Min Range: -4.0846

Max Act: 3.7010. Min Act: -0.1700

Data Index: 7376838 (Open Web Text)

Max Activating Token Index: 368

Text #16

Max Range: 4.0846. Min Range: -4.0846

Max Act: 3.6796. Min Act: -0.1700

Data Index: 6532524 (Open Web Text)

Max Activating Token Index: 767

Text #17

Max Range: 4.0846. Min Range: -4.0846

Max Act: 3.6356. Min Act: -0.1700

Data Index: 2844897 (Open Web Text)

Max Activating Token Index: 300

Text #18

Max Range: 4.0846. Min Range: -4.0846

Max Act: 3.6347. Min Act: -0.1700

Data Index: 6992962 (Open Web Text)

Max Activating Token Index: 627

Text #19

Max Range: 4.0846. Min Range: -4.0846

Max Act: 3.6591. Min Act: -0.1700

Data Index: 1470450 (Open Web Text)

Max Activating Token Index: 510