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

Dataset: Open Web Text

Neuron 21 in Layer 6

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: 3.3724. Min Range: -3.3724

Max Act: 3.3724. Min Act: -0.1700

Data Index: 1172074 (Open Web Text)

Max Activating Token Index: 941

Text #1

Max Range: 3.3724. Min Range: -3.3724

Max Act: 3.1299. Min Act: -0.1700

Data Index: 1172075 (Open Web Text)

Max Activating Token Index: 515

Text #2

Max Range: 3.3724. Min Range: -3.3724

Max Act: 3.0410. Min Act: -0.1700

Data Index: 6665656 (Open Web Text)

Max Activating Token Index: 597

Text #3

Max Range: 3.3724. Min Range: -3.3724

Max Act: 2.9747. Min Act: -0.1700

Data Index: 5684321 (Open Web Text)

Max Activating Token Index: 646

Text #4

Max Range: 3.3724. Min Range: -3.3724

Max Act: 2.9618. Min Act: -0.1700

Data Index: 6290734 (Open Web Text)

Max Activating Token Index: 464

Text #5

Max Range: 3.3724. Min Range: -3.3724

Max Act: 2.9852. Min Act: -0.1700

Data Index: 3094447 (Open Web Text)

Max Activating Token Index: 903

Text #6

Max Range: 3.3724. Min Range: -3.3724

Max Act: 2.9464. Min Act: -0.1700

Data Index: 602680 (Open Web Text)

Max Activating Token Index: 1017

Text #7

Max Range: 3.3724. Min Range: -3.3724

Max Act: 2.9469. Min Act: -0.1700

Data Index: 5348397 (Open Web Text)

Max Activating Token Index: 605

Text #8

Max Range: 3.3724. Min Range: -3.3724

Max Act: 2.9264. Min Act: -0.1700

Data Index: 1773152 (Open Web Text)

Max Activating Token Index: 120

Text #9

Max Range: 3.3724. Min Range: -3.3724

Max Act: 2.9185. Min Act: -0.1700

Data Index: 2950886 (Open Web Text)

Max Activating Token Index: 648

Text #10

Max Range: 3.3724. Min Range: -3.3724

Max Act: 2.8961. Min Act: -0.1700

Data Index: 1427396 (Open Web Text)

Max Activating Token Index: 584

Text #11

Max Range: 3.3724. Min Range: -3.3724

Max Act: 2.9023. Min Act: -0.1700

Data Index: 2703282 (Open Web Text)

Max Activating Token Index: 183

Text #12

Max Range: 3.3724. Min Range: -3.3724

Max Act: 2.8888. Min Act: -0.1700

Data Index: 3459005 (Open Web Text)

Max Activating Token Index: 108

Text #13

Max Range: 3.3724. Min Range: -3.3724

Max Act: 2.9029. Min Act: -0.1700

Data Index: 3452121 (Open Web Text)

Max Activating Token Index: 345

Text #14

Max Range: 3.3724. Min Range: -3.3724

Max Act: 2.9028. Min Act: -0.1700

Data Index: 7045727 (Open Web Text)

Max Activating Token Index: 519

Text #15

Max Range: 3.3724. Min Range: -3.3724

Max Act: 2.8671. Min Act: -0.1700

Data Index: 3118557 (Open Web Text)

Max Activating Token Index: 347

Text #16

Max Range: 3.3724. Min Range: -3.3724

Max Act: 2.8716. Min Act: -0.1700

Data Index: 6967980 (Open Web Text)

Max Activating Token Index: 797

Text #17

Max Range: 3.3724. Min Range: -3.3724

Max Act: 2.8907. Min Act: -0.1700

Data Index: 3893189 (Open Web Text)

Max Activating Token Index: 892

Text #18

Max Range: 3.3724. Min Range: -3.3724

Max Act: 2.8755. Min Act: -0.1700

Data Index: 3992540 (Open Web Text)

Max Activating Token Index: 559

Text #19

Max Range: 3.3724. Min Range: -3.3724

Max Act: 2.8979. Min Act: -0.1700

Data Index: 230823 (Open Web Text)

Max Activating Token Index: 710