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

Dataset: Open Web Text

Neuron 477 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: 4.6899. Min Range: -4.6899

Max Act: 4.6670. Min Act: -0.1700

Data Index: 906469 (Open Web Text)

Max Activating Token Index: 543

Text #1

Max Range: 4.6899. Min Range: -4.6899

Max Act: 4.6899. Min Act: -0.1700

Data Index: 7398302 (Open Web Text)

Max Activating Token Index: 861

Text #2

Max Range: 4.6899. Min Range: -4.6899

Max Act: 4.6743. Min Act: -0.1700

Data Index: 7140580 (Open Web Text)

Max Activating Token Index: 799

Text #3

Max Range: 4.6899. Min Range: -4.6899

Max Act: 4.5883. Min Act: -0.1700

Data Index: 2650877 (Open Web Text)

Max Activating Token Index: 717

Text #4

Max Range: 4.6899. Min Range: -4.6899

Max Act: 4.5334. Min Act: -0.1700

Data Index: 751458 (Open Web Text)

Max Activating Token Index: 510

Text #5

Max Range: 4.6899. Min Range: -4.6899

Max Act: 4.5249. Min Act: -0.1700

Data Index: 8244268 (Open Web Text)

Max Activating Token Index: 292

Text #6

Max Range: 4.6899. Min Range: -4.6899

Max Act: 4.5519. Min Act: -0.1700

Data Index: 5922590 (Open Web Text)

Max Activating Token Index: 695

Text #7

Max Range: 4.6899. Min Range: -4.6899

Max Act: 4.5340. Min Act: -0.1700

Data Index: 4860557 (Open Web Text)

Max Activating Token Index: 372

Text #8

Max Range: 4.6899. Min Range: -4.6899

Max Act: 4.4852. Min Act: -0.1700

Data Index: 2813804 (Open Web Text)

Max Activating Token Index: 729

Text #9

Max Range: 4.6899. Min Range: -4.6899

Max Act: 4.5070. Min Act: -0.1700

Data Index: 8004497 (Open Web Text)

Max Activating Token Index: 258

Text #10

Max Range: 4.6899. Min Range: -4.6899

Max Act: 4.4850. Min Act: -0.1700

Data Index: 4709670 (Open Web Text)

Max Activating Token Index: 401

Text #11

Max Range: 4.6899. Min Range: -4.6899

Max Act: 4.5018. Min Act: -0.1700

Data Index: 544770 (Open Web Text)

Max Activating Token Index: 694

Text #12

Max Range: 4.6899. Min Range: -4.6899

Max Act: 4.4596. Min Act: -0.1700

Data Index: 4893047 (Open Web Text)

Max Activating Token Index: 470

Text #13

Max Range: 4.6899. Min Range: -4.6899

Max Act: 4.4728. Min Act: -0.1700

Data Index: 436117 (Open Web Text)

Max Activating Token Index: 952

Text #14

Max Range: 4.6899. Min Range: -4.6899

Max Act: 4.5022. Min Act: -0.1700

Data Index: 2597594 (Open Web Text)

Max Activating Token Index: 730

Text #15

Max Range: 4.6899. Min Range: -4.6899

Max Act: 4.4549. Min Act: -0.1700

Data Index: 7662534 (Open Web Text)

Max Activating Token Index: 714

Text #16

Max Range: 4.6899. Min Range: -4.6899

Max Act: 4.4538. Min Act: -0.1700

Data Index: 4809058 (Open Web Text)

Max Activating Token Index: 348

Text #17

Max Range: 4.6899. Min Range: -4.6899

Max Act: 4.4753. Min Act: -0.1700

Data Index: 5988078 (Open Web Text)

Max Activating Token Index: 741

Text #18

Max Range: 4.6899. Min Range: -4.6899

Max Act: 4.4881. Min Act: -0.1700

Data Index: 8220155 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 4.6899. Min Range: -4.6899

Max Act: 4.4106. Min Act: -0.1700

Data Index: 6372267 (Open Web Text)

Max Activating Token Index: 910