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

Dataset: Open Web Text

Neuron 1745 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: 3.9121. Min Range: -3.9121

Max Act: 3.9087. Min Act: -0.1700

Data Index: 4506644 (Open Web Text)

Max Activating Token Index: 873

Text #1

Max Range: 3.9121. Min Range: -3.9121

Max Act: 3.9121. Min Act: -0.1700

Data Index: 1358930 (Open Web Text)

Max Activating Token Index: 421

Text #2

Max Range: 3.9121. Min Range: -3.9121

Max Act: 3.8846. Min Act: -0.1700

Data Index: 8090899 (Open Web Text)

Max Activating Token Index: 373

Text #3

Max Range: 3.9121. Min Range: -3.9121

Max Act: 3.8887. Min Act: -0.1700

Data Index: 2700091 (Open Web Text)

Max Activating Token Index: 57

Text #4

Max Range: 3.9121. Min Range: -3.9121

Max Act: 3.8535. Min Act: -0.1700

Data Index: 4666861 (Open Web Text)

Max Activating Token Index: 948

Text #5

Max Range: 3.9121. Min Range: -3.9121

Max Act: 3.8666. Min Act: -0.1700

Data Index: 7380417 (Open Web Text)

Max Activating Token Index: 329

Text #6

Max Range: 3.9121. Min Range: -3.9121

Max Act: 3.8551. Min Act: -0.1700

Data Index: 2654850 (Open Web Text)

Max Activating Token Index: 645

Text #7

Max Range: 3.9121. Min Range: -3.9121

Max Act: 3.8239. Min Act: -0.1700

Data Index: 4507671 (Open Web Text)

Max Activating Token Index: 243

Text #8

Max Range: 3.9121. Min Range: -3.9121

Max Act: 3.8614. Min Act: -0.1700

Data Index: 3706785 (Open Web Text)

Max Activating Token Index: 225

Text #9

Max Range: 3.9121. Min Range: -3.9121

Max Act: 3.8063. Min Act: -0.1700

Data Index: 5091480 (Open Web Text)

Max Activating Token Index: 310

Text #10

Max Range: 3.9121. Min Range: -3.9121

Max Act: 3.7411. Min Act: -0.1700

Data Index: 4379199 (Open Web Text)

Max Activating Token Index: 324

Text #11

Max Range: 3.9121. Min Range: -3.9121

Max Act: 3.7679. Min Act: -0.1700

Data Index: 683012 (Open Web Text)

Max Activating Token Index: 324

Text #12

Max Range: 3.9121. Min Range: -3.9121

Max Act: 3.7789. Min Act: -0.1700

Data Index: 2511735 (Open Web Text)

Max Activating Token Index: 271

Text #13

Max Range: 3.9121. Min Range: -3.9121

Max Act: 3.7651. Min Act: -0.1700

Data Index: 3852016 (Open Web Text)

Max Activating Token Index: 445

Text #14

Max Range: 3.9121. Min Range: -3.9121

Max Act: 3.7286. Min Act: -0.1700

Data Index: 858409 (Open Web Text)

Max Activating Token Index: 731

Text #15

Max Range: 3.9121. Min Range: -3.9121

Max Act: 3.7636. Min Act: -0.1700

Data Index: 8039289 (Open Web Text)

Max Activating Token Index: 387

Text #16

Max Range: 3.9121. Min Range: -3.9121

Max Act: 3.7699. Min Act: -0.1700

Data Index: 2865951 (Open Web Text)

Max Activating Token Index: 509

Text #17

Max Range: 3.9121. Min Range: -3.9121

Max Act: 3.7399. Min Act: -0.1700

Data Index: 6669274 (Open Web Text)

Max Activating Token Index: 950

Text #18

Max Range: 3.9121. Min Range: -3.9121

Max Act: 3.7641. Min Act: -0.1700

Data Index: 4487529 (Open Web Text)

Max Activating Token Index: 803

Text #19

Max Range: 3.9121. Min Range: -3.9121

Max Act: 3.7347. Min Act: -0.1700

Data Index: 2865953 (Open Web Text)

Max Activating Token Index: 416