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

Dataset: Open Web Text

Neuron 2167 in Layer 5

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: 3.8125. Min Range: -3.8125

Max Act: 3.8125. Min Act: -0.1700

Data Index: 7108421 (Open Web Text)

Max Activating Token Index: 494

Text #1

Max Range: 3.8125. Min Range: -3.8125

Max Act: 3.6470. Min Act: -0.1700

Data Index: 2944430 (Open Web Text)

Max Activating Token Index: 647

Text #2

Max Range: 3.8125. Min Range: -3.8125

Max Act: 3.6594. Min Act: -0.1700

Data Index: 931478 (Open Web Text)

Max Activating Token Index: 868

Text #3

Max Range: 3.8125. Min Range: -3.8125

Max Act: 3.6471. Min Act: -0.1700

Data Index: 8387740 (Open Web Text)

Max Activating Token Index: 879

Text #4

Max Range: 3.8125. Min Range: -3.8125

Max Act: 3.6590. Min Act: -0.1700

Data Index: 800390 (Open Web Text)

Max Activating Token Index: 718

Text #5

Max Range: 3.8125. Min Range: -3.8125

Max Act: 3.6631. Min Act: -0.1700

Data Index: 65041 (Open Web Text)

Max Activating Token Index: 472

Text #6

Max Range: 3.8125. Min Range: -3.8125

Max Act: 3.6235. Min Act: -0.1700

Data Index: 3080927 (Open Web Text)

Max Activating Token Index: 187

Text #7

Max Range: 3.8125. Min Range: -3.8125

Max Act: 3.6150. Min Act: -0.1700

Data Index: 4737125 (Open Web Text)

Max Activating Token Index: 589

Text #8

Max Range: 3.8125. Min Range: -3.8125

Max Act: 3.6332. Min Act: -0.1700

Data Index: 7713585 (Open Web Text)

Max Activating Token Index: 627

Text #9

Max Range: 3.8125. Min Range: -3.8125

Max Act: 3.6386. Min Act: -0.1700

Data Index: 4605754 (Open Web Text)

Max Activating Token Index: 236

Text #10

Max Range: 3.8125. Min Range: -3.8125

Max Act: 3.6147. Min Act: -0.1700

Data Index: 8829245 (Open Web Text)

Max Activating Token Index: 89

Text #11

Max Range: 3.8125. Min Range: -3.8125

Max Act: 3.6213. Min Act: -0.1700

Data Index: 8480138 (Open Web Text)

Max Activating Token Index: 167

Text #12

Max Range: 3.8125. Min Range: -3.8125

Max Act: 3.5942. Min Act: -0.1700

Data Index: 5533868 (Open Web Text)

Max Activating Token Index: 214

Text #13

Max Range: 3.8125. Min Range: -3.8125

Max Act: 3.6294. Min Act: -0.1700

Data Index: 6996749 (Open Web Text)

Max Activating Token Index: 754

Text #14

Max Range: 3.8125. Min Range: -3.8125

Max Act: 3.6121. Min Act: -0.1700

Data Index: 6048487 (Open Web Text)

Max Activating Token Index: 511

Text #15

Max Range: 3.8125. Min Range: -3.8125

Max Act: 3.5852. Min Act: -0.1700

Data Index: 3318266 (Open Web Text)

Max Activating Token Index: 393

Text #16

Max Range: 3.8125. Min Range: -3.8125

Max Act: 3.5827. Min Act: -0.1700

Data Index: 7589734 (Open Web Text)

Max Activating Token Index: 526

Text #17

Max Range: 3.8125. Min Range: -3.8125

Max Act: 3.5887. Min Act: -0.1700

Data Index: 6348831 (Open Web Text)

Max Activating Token Index: 830

Text #18

Max Range: 3.8125. Min Range: -3.8125

Max Act: 3.5799. Min Act: -0.1700

Data Index: 6717860 (Open Web Text)

Max Activating Token Index: 449

Text #19

Max Range: 3.8125. Min Range: -3.8125

Max Act: 3.5686. Min Act: -0.1700

Data Index: 6682766 (Open Web Text)

Max Activating Token Index: 334