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

Dataset: Open Web Text

Neuron 147 in Layer 2

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: 4.0868. Min Range: -4.0868

Max Act: 4.0868. Min Act: -0.1700

Data Index: 3194498 (Open Web Text)

Max Activating Token Index: 858

Text #1

Max Range: 4.0868. Min Range: -4.0868

Max Act: 4.0665. Min Act: -0.1700

Data Index: 6496520 (Open Web Text)

Max Activating Token Index: 614

Text #2

Max Range: 4.0868. Min Range: -4.0868

Max Act: 4.0726. Min Act: -0.1700

Data Index: 3571596 (Open Web Text)

Max Activating Token Index: 285

Text #3

Max Range: 4.0868. Min Range: -4.0868

Max Act: 4.0480. Min Act: -0.1700

Data Index: 6061273 (Open Web Text)

Max Activating Token Index: 954

Text #4

Max Range: 4.0868. Min Range: -4.0868

Max Act: 3.9634. Min Act: -0.1700

Data Index: 2596941 (Open Web Text)

Max Activating Token Index: 717

Text #5

Max Range: 4.0868. Min Range: -4.0868

Max Act: 3.9974. Min Act: -0.1700

Data Index: 7524192 (Open Web Text)

Max Activating Token Index: 906

Text #6

Max Range: 4.0868. Min Range: -4.0868

Max Act: 3.9451. Min Act: -0.1700

Data Index: 6808444 (Open Web Text)

Max Activating Token Index: 461

Text #7

Max Range: 4.0868. Min Range: -4.0868

Max Act: 3.9352. Min Act: -0.1700

Data Index: 1580831 (Open Web Text)

Max Activating Token Index: 242

Text #8

Max Range: 4.0868. Min Range: -4.0868

Max Act: 3.9612. Min Act: -0.1700

Data Index: 3108054 (Open Web Text)

Max Activating Token Index: 987

Text #9

Max Range: 4.0868. Min Range: -4.0868

Max Act: 3.9197. Min Act: -0.1700

Data Index: 6272131 (Open Web Text)

Max Activating Token Index: 680

Text #10

Max Range: 4.0868. Min Range: -4.0868

Max Act: 3.9521. Min Act: -0.1700

Data Index: 7765955 (Open Web Text)

Max Activating Token Index: 347

Text #11

Max Range: 4.0868. Min Range: -4.0868

Max Act: 3.9621. Min Act: -0.1700

Data Index: 4921063 (Open Web Text)

Max Activating Token Index: 71

Text #12

Max Range: 4.0868. Min Range: -4.0868

Max Act: 4.0094. Min Act: -0.1700

Data Index: 1469713 (Open Web Text)

Max Activating Token Index: 976

Text #13

Max Range: 4.0868. Min Range: -4.0868

Max Act: 3.9850. Min Act: -0.1700

Data Index: 2870507 (Open Web Text)

Max Activating Token Index: 508

Text #14

Max Range: 4.0868. Min Range: -4.0868

Max Act: 3.9122. Min Act: -0.1700

Data Index: 2139911 (Open Web Text)

Max Activating Token Index: 481

Text #15

Max Range: 4.0868. Min Range: -4.0868

Max Act: 3.8978. Min Act: -0.1700

Data Index: 8222927 (Open Web Text)

Max Activating Token Index: 60

Text #16

Max Range: 4.0868. Min Range: -4.0868

Max Act: 3.9372. Min Act: -0.1700

Data Index: 8826444 (Open Web Text)

Max Activating Token Index: 269

Text #17

Max Range: 4.0868. Min Range: -4.0868

Max Act: 3.8819. Min Act: -0.1700

Data Index: 1018611 (Open Web Text)

Max Activating Token Index: 112

Text #18

Max Range: 4.0868. Min Range: -4.0868

Max Act: 3.8898. Min Act: -0.1700

Data Index: 3657909 (Open Web Text)

Max Activating Token Index: 582

Text #19

Max Range: 4.0868. Min Range: -4.0868

Max Act: 3.8723. Min Act: -0.1700

Data Index: 3101615 (Open Web Text)

Max Activating Token Index: 735