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

Dataset: Open Web Text

Neuron 927 in Layer 3

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: 3.9730. Min Range: -3.9730

Max Act: 3.9730. Min Act: -0.1700

Data Index: 5085952 (Open Web Text)

Max Activating Token Index: 390

Text #1

Max Range: 3.9730. Min Range: -3.9730

Max Act: 3.9453. Min Act: -0.1700

Data Index: 4895932 (Open Web Text)

Max Activating Token Index: 437

Text #2

Max Range: 3.9730. Min Range: -3.9730

Max Act: 3.9495. Min Act: -0.1700

Data Index: 800873 (Open Web Text)

Max Activating Token Index: 375

Text #3

Max Range: 3.9730. Min Range: -3.9730

Max Act: 3.9261. Min Act: -0.1700

Data Index: 8352042 (Open Web Text)

Max Activating Token Index: 88

Text #4

Max Range: 3.9730. Min Range: -3.9730

Max Act: 3.8957. Min Act: -0.1700

Data Index: 3408971 (Open Web Text)

Max Activating Token Index: 213

Text #5

Max Range: 3.9730. Min Range: -3.9730

Max Act: 3.8990. Min Act: -0.1700

Data Index: 1440769 (Open Web Text)

Max Activating Token Index: 457

Text #6

Max Range: 3.9730. Min Range: -3.9730

Max Act: 3.8707. Min Act: -0.1700

Data Index: 1125947 (Open Web Text)

Max Activating Token Index: 292

Text #7

Max Range: 3.9730. Min Range: -3.9730

Max Act: 3.8950. Min Act: -0.1700

Data Index: 8708453 (Open Web Text)

Max Activating Token Index: 364

Text #8

Max Range: 3.9730. Min Range: -3.9730

Max Act: 3.8470. Min Act: -0.1700

Data Index: 3621366 (Open Web Text)

Max Activating Token Index: 811

Text #9

Max Range: 3.9730. Min Range: -3.9730

Max Act: 3.7913. Min Act: -0.1700

Data Index: 8275498 (Open Web Text)

Max Activating Token Index: 849

Text #10

Max Range: 3.9730. Min Range: -3.9730

Max Act: 3.8100. Min Act: -0.1700

Data Index: 1279807 (Open Web Text)

Max Activating Token Index: 382

Text #11

Max Range: 3.9730. Min Range: -3.9730

Max Act: 3.8329. Min Act: -0.1700

Data Index: 485808 (Open Web Text)

Max Activating Token Index: 356

Text #12

Max Range: 3.9730. Min Range: -3.9730

Max Act: 3.8034. Min Act: -0.1700

Data Index: 8790724 (Open Web Text)

Max Activating Token Index: 348

Text #13

Max Range: 3.9730. Min Range: -3.9730

Max Act: 3.8323. Min Act: -0.1700

Data Index: 7150931 (Open Web Text)

Max Activating Token Index: 834

Text #14

Max Range: 3.9730. Min Range: -3.9730

Max Act: 3.8014. Min Act: -0.1700

Data Index: 7452667 (Open Web Text)

Max Activating Token Index: 309

Text #15

Max Range: 3.9730. Min Range: -3.9730

Max Act: 3.7961. Min Act: -0.1700

Data Index: 5492190 (Open Web Text)

Max Activating Token Index: 389

Text #16

Max Range: 3.9730. Min Range: -3.9730

Max Act: 3.7954. Min Act: -0.1700

Data Index: 2562762 (Open Web Text)

Max Activating Token Index: 789

Text #17

Max Range: 3.9730. Min Range: -3.9730

Max Act: 3.7835. Min Act: -0.1700

Data Index: 3935680 (Open Web Text)

Max Activating Token Index: 914

Text #18

Max Range: 3.9730. Min Range: -3.9730

Max Act: 3.7540. Min Act: -0.1700

Data Index: 3055364 (Open Web Text)

Max Activating Token Index: 591

Text #19

Max Range: 3.9730. Min Range: -3.9730

Max Act: 3.7623. Min Act: -0.1700

Data Index: 4615000 (Open Web Text)

Max Activating Token Index: 377