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

Dataset: Open Web Text

Neuron 449 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: 3.4689. Min Range: -3.4689

Max Act: 3.4419. Min Act: -0.1700

Data Index: 1045837 (Open Web Text)

Max Activating Token Index: 441

Text #1

Max Range: 3.4689. Min Range: -3.4689

Max Act: 3.4437. Min Act: -0.1700

Data Index: 6374701 (Open Web Text)

Max Activating Token Index: 372

Text #2

Max Range: 3.4689. Min Range: -3.4689

Max Act: 3.4689. Min Act: -0.1700

Data Index: 4879673 (Open Web Text)

Max Activating Token Index: 517

Text #3

Max Range: 3.4689. Min Range: -3.4689

Max Act: 3.4080. Min Act: -0.1700

Data Index: 2479196 (Open Web Text)

Max Activating Token Index: 83

Text #4

Max Range: 3.4689. Min Range: -3.4689

Max Act: 3.3577. Min Act: -0.1700

Data Index: 162036 (Open Web Text)

Max Activating Token Index: 898

Text #5

Max Range: 3.4689. Min Range: -3.4689

Max Act: 3.3702. Min Act: -0.1700

Data Index: 2155441 (Open Web Text)

Max Activating Token Index: 552

Text #6

Max Range: 3.4689. Min Range: -3.4689

Max Act: 3.4182. Min Act: -0.1700

Data Index: 7965999 (Open Web Text)

Max Activating Token Index: 674

Text #7

Max Range: 3.4689. Min Range: -3.4689

Max Act: 3.3440. Min Act: -0.1700

Data Index: 833902 (Open Web Text)

Max Activating Token Index: 715

Text #8

Max Range: 3.4689. Min Range: -3.4689

Max Act: 3.3286. Min Act: -0.1700

Data Index: 554760 (Open Web Text)

Max Activating Token Index: 488

Text #9

Max Range: 3.4689. Min Range: -3.4689

Max Act: 3.2876. Min Act: -0.1700

Data Index: 6713860 (Open Web Text)

Max Activating Token Index: 308

Text #10

Max Range: 3.4689. Min Range: -3.4689

Max Act: 3.3363. Min Act: -0.1700

Data Index: 4808743 (Open Web Text)

Max Activating Token Index: 115

Text #11

Max Range: 3.4689. Min Range: -3.4689

Max Act: 3.2773. Min Act: -0.1700

Data Index: 1493034 (Open Web Text)

Max Activating Token Index: 451

Text #12

Max Range: 3.4689. Min Range: -3.4689

Max Act: 3.3072. Min Act: -0.1700

Data Index: 8281795 (Open Web Text)

Max Activating Token Index: 186

Text #13

Max Range: 3.4689. Min Range: -3.4689

Max Act: 3.2855. Min Act: -0.1700

Data Index: 2191690 (Open Web Text)

Max Activating Token Index: 33

Text #14

Max Range: 3.4689. Min Range: -3.4689

Max Act: 3.3529. Min Act: -0.1700

Data Index: 8266837 (Open Web Text)

Max Activating Token Index: 334

Text #15

Max Range: 3.4689. Min Range: -3.4689

Max Act: 3.2989. Min Act: -0.1700

Data Index: 555950 (Open Web Text)

Max Activating Token Index: 700

Text #16

Max Range: 3.4689. Min Range: -3.4689

Max Act: 3.3139. Min Act: -0.1700

Data Index: 4362728 (Open Web Text)

Max Activating Token Index: 654

Text #17

Max Range: 3.4689. Min Range: -3.4689

Max Act: 3.2890. Min Act: -0.1700

Data Index: 3368374 (Open Web Text)

Max Activating Token Index: 840

Text #18

Max Range: 3.4689. Min Range: -3.4689

Max Act: 3.3021. Min Act: -0.1700

Data Index: 809391 (Open Web Text)

Max Activating Token Index: 87

Text #19

Max Range: 3.4689. Min Range: -3.4689

Max Act: 3.2808. Min Act: -0.1700

Data Index: 3205769 (Open Web Text)

Max Activating Token Index: 376