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

Dataset: Open Web Text

Neuron 1076 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: 3.2696. Min Range: -3.2696

Max Act: 3.2696. Min Act: -0.1700

Data Index: 3782447 (Open Web Text)

Max Activating Token Index: 558

Text #1

Max Range: 3.2696. Min Range: -3.2696

Max Act: 3.1277. Min Act: -0.1700

Data Index: 6131205 (Open Web Text)

Max Activating Token Index: 561

Text #2

Max Range: 3.2696. Min Range: -3.2696

Max Act: 3.1013. Min Act: -0.1700

Data Index: 5598836 (Open Web Text)

Max Activating Token Index: 300

Text #3

Max Range: 3.2696. Min Range: -3.2696

Max Act: 3.0862. Min Act: -0.1700

Data Index: 4604496 (Open Web Text)

Max Activating Token Index: 200

Text #4

Max Range: 3.2696. Min Range: -3.2696

Max Act: 3.0790. Min Act: -0.1700

Data Index: 2531251 (Open Web Text)

Max Activating Token Index: 349

Text #5

Max Range: 3.2696. Min Range: -3.2696

Max Act: 3.0808. Min Act: -0.1700

Data Index: 3280875 (Open Web Text)

Max Activating Token Index: 894

Text #6

Max Range: 3.2696. Min Range: -3.2696

Max Act: 3.0179. Min Act: -0.1700

Data Index: 6151259 (Open Web Text)

Max Activating Token Index: 734

Text #7

Max Range: 3.2696. Min Range: -3.2696

Max Act: 2.9823. Min Act: -0.1700

Data Index: 1570215 (Open Web Text)

Max Activating Token Index: 211

Text #8

Max Range: 3.2696. Min Range: -3.2696

Max Act: 3.0287. Min Act: -0.1700

Data Index: 3710561 (Open Web Text)

Max Activating Token Index: 124

Text #9

Max Range: 3.2696. Min Range: -3.2696

Max Act: 2.9889. Min Act: -0.1700

Data Index: 4822751 (Open Web Text)

Max Activating Token Index: 986

Text #10

Max Range: 3.2696. Min Range: -3.2696

Max Act: 2.9385. Min Act: -0.1700

Data Index: 1865420 (Open Web Text)

Max Activating Token Index: 471

Text #11

Max Range: 3.2696. Min Range: -3.2696

Max Act: 2.9920. Min Act: -0.1700

Data Index: 6792336 (Open Web Text)

Max Activating Token Index: 768

Text #12

Max Range: 3.2696. Min Range: -3.2696

Max Act: 2.9240. Min Act: -0.1700

Data Index: 2489250 (Open Web Text)

Max Activating Token Index: 488

Text #13

Max Range: 3.2696. Min Range: -3.2696

Max Act: 2.9343. Min Act: -0.1700

Data Index: 1989450 (Open Web Text)

Max Activating Token Index: 64

Text #14

Max Range: 3.2696. Min Range: -3.2696

Max Act: 2.9633. Min Act: -0.1700

Data Index: 1015114 (Open Web Text)

Max Activating Token Index: 745

Text #15

Max Range: 3.2696. Min Range: -3.2696

Max Act: 2.9098. Min Act: -0.1700

Data Index: 8717827 (Open Web Text)

Max Activating Token Index: 638

Text #16

Max Range: 3.2696. Min Range: -3.2696

Max Act: 3.0010. Min Act: -0.1700

Data Index: 2840431 (Open Web Text)

Max Activating Token Index: 536

Text #17

Max Range: 3.2696. Min Range: -3.2696

Max Act: 2.9785. Min Act: -0.1700

Data Index: 6644482 (Open Web Text)

Max Activating Token Index: 439

Text #18

Max Range: 3.2696. Min Range: -3.2696

Max Act: 2.8804. Min Act: -0.1700

Data Index: 7807648 (Open Web Text)

Max Activating Token Index: 253

Text #19

Max Range: 3.2696. Min Range: -3.2696

Max Act: 2.8737. Min Act: -0.1699

Data Index: 826791 (Open Web Text)

Max Activating Token Index: 690