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

Dataset: Open Web Text

Neuron 2137 in Layer 5

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: 3.1861. Min Range: -3.1861

Max Act: 3.1861. Min Act: -0.1700

Data Index: 1222870 (Open Web Text)

Max Activating Token Index: 235

Text #1

Max Range: 3.1861. Min Range: -3.1861

Max Act: 3.0582. Min Act: -0.1700

Data Index: 6839570 (Open Web Text)

Max Activating Token Index: 766

Text #2

Max Range: 3.1861. Min Range: -3.1861

Max Act: 3.0524. Min Act: -0.1700

Data Index: 6256427 (Open Web Text)

Max Activating Token Index: 780

Text #3

Max Range: 3.1861. Min Range: -3.1861

Max Act: 3.0295. Min Act: -0.1700

Data Index: 270328 (Open Web Text)

Max Activating Token Index: 677

Text #4

Max Range: 3.1861. Min Range: -3.1861

Max Act: 3.0106. Min Act: -0.1700

Data Index: 525880 (Open Web Text)

Max Activating Token Index: 559

Text #5

Max Range: 3.1861. Min Range: -3.1861

Max Act: 3.0326. Min Act: -0.1700

Data Index: 5131878 (Open Web Text)

Max Activating Token Index: 510

Text #6

Max Range: 3.1861. Min Range: -3.1861

Max Act: 2.9763. Min Act: -0.1700

Data Index: 8729990 (Open Web Text)

Max Activating Token Index: 618

Text #7

Max Range: 3.1861. Min Range: -3.1861

Max Act: 2.9742. Min Act: -0.1700

Data Index: 2508076 (Open Web Text)

Max Activating Token Index: 148

Text #8

Max Range: 3.1861. Min Range: -3.1861

Max Act: 2.9492. Min Act: -0.1700

Data Index: 2347116 (Open Web Text)

Max Activating Token Index: 85

Text #9

Max Range: 3.1861. Min Range: -3.1861

Max Act: 2.9550. Min Act: -0.1700

Data Index: 6132388 (Open Web Text)

Max Activating Token Index: 313

Text #10

Max Range: 3.1861. Min Range: -3.1861

Max Act: 2.9563. Min Act: -0.1700

Data Index: 2797533 (Open Web Text)

Max Activating Token Index: 940

Text #11

Max Range: 3.1861. Min Range: -3.1861

Max Act: 2.9580. Min Act: -0.1700

Data Index: 4354611 (Open Web Text)

Max Activating Token Index: 319

Text #12

Max Range: 3.1861. Min Range: -3.1861

Max Act: 2.9349. Min Act: -0.1700

Data Index: 6330032 (Open Web Text)

Max Activating Token Index: 509

Text #13

Max Range: 3.1861. Min Range: -3.1861

Max Act: 2.9103. Min Act: -0.1700

Data Index: 5993611 (Open Web Text)

Max Activating Token Index: 879

Text #14

Max Range: 3.1861. Min Range: -3.1861

Max Act: 2.9348. Min Act: -0.1700

Data Index: 478565 (Open Web Text)

Max Activating Token Index: 635

Text #15

Max Range: 3.1861. Min Range: -3.1861

Max Act: 2.9137. Min Act: -0.1700

Data Index: 274971 (Open Web Text)

Max Activating Token Index: 1020

Text #16

Max Range: 3.1861. Min Range: -3.1861

Max Act: 2.9385. Min Act: -0.1700

Data Index: 8687283 (Open Web Text)

Max Activating Token Index: 676

Text #17

Max Range: 3.1861. Min Range: -3.1861

Max Act: 2.9302. Min Act: -0.1700

Data Index: 1798998 (Open Web Text)

Max Activating Token Index: 391

Text #18

Max Range: 3.1861. Min Range: -3.1861

Max Act: 2.9225. Min Act: -0.1700

Data Index: 317800 (Open Web Text)

Max Activating Token Index: 869

Text #19

Max Range: 3.1861. Min Range: -3.1861

Max Act: 2.9292. Min Act: -0.1700

Data Index: 593753 (Open Web Text)

Max Activating Token Index: 293