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

Dataset: Open Web Text

Neuron 2998 in Layer 2

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: 3.4782. Min Range: -3.4782

Max Act: 3.4782. Min Act: -0.1700

Data Index: 6737008 (Open Web Text)

Max Activating Token Index: 500

Text #1

Max Range: 3.4782. Min Range: -3.4782

Max Act: 3.3514. Min Act: -0.1700

Data Index: 1272991 (Open Web Text)

Max Activating Token Index: 182

Text #2

Max Range: 3.4782. Min Range: -3.4782

Max Act: 3.3066. Min Act: -0.1700

Data Index: 5751156 (Open Web Text)

Max Activating Token Index: 462

Text #3

Max Range: 3.4782. Min Range: -3.4782

Max Act: 3.3165. Min Act: -0.1700

Data Index: 6286494 (Open Web Text)

Max Activating Token Index: 441

Text #4

Max Range: 3.4782. Min Range: -3.4782

Max Act: 3.2665. Min Act: -0.1700

Data Index: 4445914 (Open Web Text)

Max Activating Token Index: 433

Text #5

Max Range: 3.4782. Min Range: -3.4782

Max Act: 3.2813. Min Act: -0.1700

Data Index: 2108987 (Open Web Text)

Max Activating Token Index: 257

Text #6

Max Range: 3.4782. Min Range: -3.4782

Max Act: 3.2568. Min Act: -0.1700

Data Index: 3622965 (Open Web Text)

Max Activating Token Index: 133

Text #7

Max Range: 3.4782. Min Range: -3.4782

Max Act: 3.2633. Min Act: -0.1700

Data Index: 1323072 (Open Web Text)

Max Activating Token Index: 444

Text #8

Max Range: 3.4782. Min Range: -3.4782

Max Act: 3.2812. Min Act: -0.1700

Data Index: 5973491 (Open Web Text)

Max Activating Token Index: 205

Text #9

Max Range: 3.4782. Min Range: -3.4782

Max Act: 3.2456. Min Act: -0.1700

Data Index: 5817569 (Open Web Text)

Max Activating Token Index: 302

Text #10

Max Range: 3.4782. Min Range: -3.4782

Max Act: 3.2624. Min Act: -0.1700

Data Index: 2711724 (Open Web Text)

Max Activating Token Index: 97

Text #11

Max Range: 3.4782. Min Range: -3.4782

Max Act: 3.2430. Min Act: -0.1700

Data Index: 2552476 (Open Web Text)

Max Activating Token Index: 652

Text #12

Max Range: 3.4782. Min Range: -3.4782

Max Act: 3.2331. Min Act: -0.1700

Data Index: 7690695 (Open Web Text)

Max Activating Token Index: 133

Text #13

Max Range: 3.4782. Min Range: -3.4782

Max Act: 3.2259. Min Act: -0.1700

Data Index: 4462595 (Open Web Text)

Max Activating Token Index: 693

Text #14

Max Range: 3.4782. Min Range: -3.4782

Max Act: 3.2268. Min Act: -0.1700

Data Index: 6096290 (Open Web Text)

Max Activating Token Index: 901

Text #15

Max Range: 3.4782. Min Range: -3.4782

Max Act: 3.2010. Min Act: -0.1700

Data Index: 2771737 (Open Web Text)

Max Activating Token Index: 560

Text #16

Max Range: 3.4782. Min Range: -3.4782

Max Act: 3.2184. Min Act: -0.1700

Data Index: 4258983 (Open Web Text)

Max Activating Token Index: 299

Text #17

Max Range: 3.4782. Min Range: -3.4782

Max Act: 3.1935. Min Act: -0.1700

Data Index: 3529180 (Open Web Text)

Max Activating Token Index: 466

Text #18

Max Range: 3.4782. Min Range: -3.4782

Max Act: 3.2070. Min Act: -0.1700

Data Index: 6292524 (Open Web Text)

Max Activating Token Index: 408

Text #19

Max Range: 3.4782. Min Range: -3.4782

Max Act: 3.1938. Min Act: -0.1700

Data Index: 4445913 (Open Web Text)

Max Activating Token Index: 904