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

Dataset: Open Web Text

Neuron 771 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: 4.6856. Min Range: -4.6856

Max Act: 4.6614. Min Act: -0.1700

Data Index: 8307302 (Open Web Text)

Max Activating Token Index: 540

Text #1

Max Range: 4.6856. Min Range: -4.6856

Max Act: 4.6856. Min Act: -0.1700

Data Index: 1452081 (Open Web Text)

Max Activating Token Index: 545

Text #2

Max Range: 4.6856. Min Range: -4.6856

Max Act: 4.6350. Min Act: -0.1700

Data Index: 4575749 (Open Web Text)

Max Activating Token Index: 597

Text #3

Max Range: 4.6856. Min Range: -4.6856

Max Act: 4.6490. Min Act: -0.1700

Data Index: 3578829 (Open Web Text)

Max Activating Token Index: 637

Text #4

Max Range: 4.6856. Min Range: -4.6856

Max Act: 4.6459. Min Act: -0.1700

Data Index: 5433867 (Open Web Text)

Max Activating Token Index: 356

Text #5

Max Range: 4.6856. Min Range: -4.6856

Max Act: 4.6009. Min Act: -0.1700

Data Index: 4403402 (Open Web Text)

Max Activating Token Index: 727

Text #6

Max Range: 4.6856. Min Range: -4.6856

Max Act: 4.5982. Min Act: -0.1700

Data Index: 662797 (Open Web Text)

Max Activating Token Index: 467

Text #7

Max Range: 4.6856. Min Range: -4.6856

Max Act: 4.5912. Min Act: -0.1700

Data Index: 4781869 (Open Web Text)

Max Activating Token Index: 545

Text #8

Max Range: 4.6856. Min Range: -4.6856

Max Act: 4.6085. Min Act: -0.1700

Data Index: 2745083 (Open Web Text)

Max Activating Token Index: 9

Text #9

Max Range: 4.6856. Min Range: -4.6856

Max Act: 4.5657. Min Act: -0.1700

Data Index: 6262911 (Open Web Text)

Max Activating Token Index: 202

Text #10

Max Range: 4.6856. Min Range: -4.6856

Max Act: 4.5896. Min Act: -0.1700

Data Index: 4298450 (Open Web Text)

Max Activating Token Index: 960

Text #11

Max Range: 4.6856. Min Range: -4.6856

Max Act: 4.5934. Min Act: -0.1700

Data Index: 6039818 (Open Web Text)

Max Activating Token Index: 464

Text #12

Max Range: 4.6856. Min Range: -4.6856

Max Act: 4.5865. Min Act: -0.1700

Data Index: 5911875 (Open Web Text)

Max Activating Token Index: 84

Text #13

Max Range: 4.6856. Min Range: -4.6856

Max Act: 4.5800. Min Act: -0.1700

Data Index: 5421229 (Open Web Text)

Max Activating Token Index: 851

Text #14

Max Range: 4.6856. Min Range: -4.6856

Max Act: 4.5988. Min Act: -0.1700

Data Index: 4685324 (Open Web Text)

Max Activating Token Index: 357

Text #15

Max Range: 4.6856. Min Range: -4.6856

Max Act: 4.5664. Min Act: -0.1700

Data Index: 4648711 (Open Web Text)

Max Activating Token Index: 41

Text #16

Max Range: 4.6856. Min Range: -4.6856

Max Act: 4.5709. Min Act: -0.1700

Data Index: 1423257 (Open Web Text)

Max Activating Token Index: 81

Text #17

Max Range: 4.6856. Min Range: -4.6856

Max Act: 4.5811. Min Act: -0.1700

Data Index: 2634908 (Open Web Text)

Max Activating Token Index: 841

Text #18

Max Range: 4.6856. Min Range: -4.6856

Max Act: 4.5730. Min Act: -0.1700

Data Index: 2564942 (Open Web Text)

Max Activating Token Index: 318

Text #19

Max Range: 4.6856. Min Range: -4.6856

Max Act: 4.5812. Min Act: -0.1700

Data Index: 958879 (Open Web Text)

Max Activating Token Index: 85