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

Dataset: Open Web Text

Neuron 2526 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: 4.4655. Min Range: -4.4655

Max Act: 4.4655. Min Act: -0.1700

Data Index: 589719 (Open Web Text)

Max Activating Token Index: 827

Text #1

Max Range: 4.4655. Min Range: -4.4655

Max Act: 4.3703. Min Act: -0.1700

Data Index: 6768975 (Open Web Text)

Max Activating Token Index: 296

Text #2

Max Range: 4.4655. Min Range: -4.4655

Max Act: 4.3479. Min Act: -0.1700

Data Index: 4277789 (Open Web Text)

Max Activating Token Index: 903

Text #3

Max Range: 4.4655. Min Range: -4.4655

Max Act: 4.3591. Min Act: -0.1700

Data Index: 4629655 (Open Web Text)

Max Activating Token Index: 122

Text #4

Max Range: 4.4655. Min Range: -4.4655

Max Act: 4.3375. Min Act: -0.1700

Data Index: 4380476 (Open Web Text)

Max Activating Token Index: 876

Text #5

Max Range: 4.4655. Min Range: -4.4655

Max Act: 4.2868. Min Act: -0.1700

Data Index: 1320842 (Open Web Text)

Max Activating Token Index: 497

Text #6

Max Range: 4.4655. Min Range: -4.4655

Max Act: 4.3427. Min Act: -0.1700

Data Index: 4151552 (Open Web Text)

Max Activating Token Index: 392

Text #7

Max Range: 4.4655. Min Range: -4.4655

Max Act: 4.3049. Min Act: -0.1700

Data Index: 5617281 (Open Web Text)

Max Activating Token Index: 796

Text #8

Max Range: 4.4655. Min Range: -4.4655

Max Act: 4.2988. Min Act: -0.1700

Data Index: 2085346 (Open Web Text)

Max Activating Token Index: 914

Text #9

Max Range: 4.4655. Min Range: -4.4655

Max Act: 4.3213. Min Act: -0.1700

Data Index: 1971513 (Open Web Text)

Max Activating Token Index: 390

Text #10

Max Range: 4.4655. Min Range: -4.4655

Max Act: 4.3112. Min Act: -0.1700

Data Index: 5194261 (Open Web Text)

Max Activating Token Index: 1009

Text #11

Max Range: 4.4655. Min Range: -4.4655

Max Act: 4.3247. Min Act: -0.1700

Data Index: 1429327 (Open Web Text)

Max Activating Token Index: 942

Text #12

Max Range: 4.4655. Min Range: -4.4655

Max Act: 4.2767. Min Act: -0.1700

Data Index: 2097983 (Open Web Text)

Max Activating Token Index: 822

Text #13

Max Range: 4.4655. Min Range: -4.4655

Max Act: 4.2717. Min Act: -0.1700

Data Index: 6375896 (Open Web Text)

Max Activating Token Index: 345

Text #14

Max Range: 4.4655. Min Range: -4.4655

Max Act: 4.2594. Min Act: -0.1700

Data Index: 6830838 (Open Web Text)

Max Activating Token Index: 535

Text #15

Max Range: 4.4655. Min Range: -4.4655

Max Act: 4.3043. Min Act: -0.1700

Data Index: 313026 (Open Web Text)

Max Activating Token Index: 546

Text #16

Max Range: 4.4655. Min Range: -4.4655

Max Act: 4.2827. Min Act: -0.1700

Data Index: 7091498 (Open Web Text)

Max Activating Token Index: 693

Text #17

Max Range: 4.4655. Min Range: -4.4655

Max Act: 4.2665. Min Act: -0.1700

Data Index: 886786 (Open Web Text)

Max Activating Token Index: 539

Text #18

Max Range: 4.4655. Min Range: -4.4655

Max Act: 4.2777. Min Act: -0.1700

Data Index: 2685585 (Open Web Text)

Max Activating Token Index: 173

Text #19

Max Range: 4.4655. Min Range: -4.4655

Max Act: 4.2604. Min Act: -0.1700

Data Index: 1672170 (Open Web Text)

Max Activating Token Index: 79