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

Dataset: Open Web Text

Neuron 687 in Layer 1

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: 5.1591. Min Range: -5.1591

Max Act: 5.1591. Min Act: -0.1700

Data Index: 6191285 (Open Web Text)

Max Activating Token Index: 382

Text #1

Max Range: 5.1591. Min Range: -5.1591

Max Act: 5.0790. Min Act: -0.1700

Data Index: 5087988 (Open Web Text)

Max Activating Token Index: 501

Text #2

Max Range: 5.1591. Min Range: -5.1591

Max Act: 5.0061. Min Act: -0.1700

Data Index: 6583577 (Open Web Text)

Max Activating Token Index: 464

Text #3

Max Range: 5.1591. Min Range: -5.1591

Max Act: 5.0089. Min Act: -0.1700

Data Index: 4582492 (Open Web Text)

Max Activating Token Index: 627

Text #4

Max Range: 5.1591. Min Range: -5.1591

Max Act: 4.9691. Min Act: -0.1700

Data Index: 4980390 (Open Web Text)

Max Activating Token Index: 665

Text #5

Max Range: 5.1591. Min Range: -5.1591

Max Act: 4.9565. Min Act: -0.1700

Data Index: 6672447 (Open Web Text)

Max Activating Token Index: 605

Text #6

Max Range: 5.1591. Min Range: -5.1591

Max Act: 4.9199. Min Act: -0.1700

Data Index: 693393 (Open Web Text)

Max Activating Token Index: 368

Text #7

Max Range: 5.1591. Min Range: -5.1591

Max Act: 4.9547. Min Act: -0.1700

Data Index: 1876203 (Open Web Text)

Max Activating Token Index: 708

Text #8

Max Range: 5.1591. Min Range: -5.1591

Max Act: 4.9212. Min Act: -0.1700

Data Index: 8338956 (Open Web Text)

Max Activating Token Index: 807

Text #9

Max Range: 5.1591. Min Range: -5.1591

Max Act: 4.9007. Min Act: -0.1700

Data Index: 3868452 (Open Web Text)

Max Activating Token Index: 673

Text #10

Max Range: 5.1591. Min Range: -5.1591

Max Act: 4.9305. Min Act: -0.1700

Data Index: 7092224 (Open Web Text)

Max Activating Token Index: 478

Text #11

Max Range: 5.1591. Min Range: -5.1591

Max Act: 4.9260. Min Act: -0.1700

Data Index: 8506100 (Open Web Text)

Max Activating Token Index: 670

Text #12

Max Range: 5.1591. Min Range: -5.1591

Max Act: 4.9058. Min Act: -0.1700

Data Index: 65652 (Open Web Text)

Max Activating Token Index: 592

Text #13

Max Range: 5.1591. Min Range: -5.1591

Max Act: 4.8904. Min Act: -0.1700

Data Index: 6385143 (Open Web Text)

Max Activating Token Index: 561

Text #14

Max Range: 5.1591. Min Range: -5.1591

Max Act: 4.8606. Min Act: -0.1700

Data Index: 8080887 (Open Web Text)

Max Activating Token Index: 852

Text #15

Max Range: 5.1591. Min Range: -5.1591

Max Act: 4.8723. Min Act: -0.1700

Data Index: 4989090 (Open Web Text)

Max Activating Token Index: 675

Text #16

Max Range: 5.1591. Min Range: -5.1591

Max Act: 4.8919. Min Act: -0.1700

Data Index: 3622750 (Open Web Text)

Max Activating Token Index: 794

Text #17

Max Range: 5.1591. Min Range: -5.1591

Max Act: 4.8456. Min Act: -0.1700

Data Index: 7890172 (Open Web Text)

Max Activating Token Index: 685

Text #18

Max Range: 5.1591. Min Range: -5.1591

Max Act: 4.8523. Min Act: -0.1700

Data Index: 666255 (Open Web Text)

Max Activating Token Index: 92

Text #19

Max Range: 5.1591. Min Range: -5.1591

Max Act: 4.8033. Min Act: -0.1700

Data Index: 2483950 (Open Web Text)

Max Activating Token Index: 547