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

Dataset: Open Web Text

Neuron 584 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: 4.3801. Min Range: -4.3801

Max Act: 4.3801. Min Act: -0.1700

Data Index: 2836392 (Open Web Text)

Max Activating Token Index: 637

Text #1

Max Range: 4.3801. Min Range: -4.3801

Max Act: 4.1944. Min Act: -0.1700

Data Index: 5602117 (Open Web Text)

Max Activating Token Index: 601

Text #2

Max Range: 4.3801. Min Range: -4.3801

Max Act: 4.1690. Min Act: -0.1700

Data Index: 604802 (Open Web Text)

Max Activating Token Index: 861

Text #3

Max Range: 4.3801. Min Range: -4.3801

Max Act: 4.2227. Min Act: -0.1700

Data Index: 926244 (Open Web Text)

Max Activating Token Index: 660

Text #4

Max Range: 4.3801. Min Range: -4.3801

Max Act: 4.2203. Min Act: -0.1700

Data Index: 6228026 (Open Web Text)

Max Activating Token Index: 530

Text #5

Max Range: 4.3801. Min Range: -4.3801

Max Act: 4.1985. Min Act: -0.1700

Data Index: 8432588 (Open Web Text)

Max Activating Token Index: 586

Text #6

Max Range: 4.3801. Min Range: -4.3801

Max Act: 4.2260. Min Act: -0.1700

Data Index: 2294504 (Open Web Text)

Max Activating Token Index: 590

Text #7

Max Range: 4.3801. Min Range: -4.3801

Max Act: 4.2027. Min Act: -0.1700

Data Index: 6095570 (Open Web Text)

Max Activating Token Index: 713

Text #8

Max Range: 4.3801. Min Range: -4.3801

Max Act: 4.2177. Min Act: -0.1700

Data Index: 6106469 (Open Web Text)

Max Activating Token Index: 278

Text #9

Max Range: 4.3801. Min Range: -4.3801

Max Act: 4.1918. Min Act: -0.1700

Data Index: 541907 (Open Web Text)

Max Activating Token Index: 697

Text #10

Max Range: 4.3801. Min Range: -4.3801

Max Act: 4.1283. Min Act: -0.1700

Data Index: 4739774 (Open Web Text)

Max Activating Token Index: 624

Text #11

Max Range: 4.3801. Min Range: -4.3801

Max Act: 4.1702. Min Act: -0.1700

Data Index: 3475380 (Open Web Text)

Max Activating Token Index: 882

Text #12

Max Range: 4.3801. Min Range: -4.3801

Max Act: 4.1902. Min Act: -0.1700

Data Index: 1941955 (Open Web Text)

Max Activating Token Index: 521

Text #13

Max Range: 4.3801. Min Range: -4.3801

Max Act: 4.1813. Min Act: -0.1700

Data Index: 2851966 (Open Web Text)

Max Activating Token Index: 634

Text #14

Max Range: 4.3801. Min Range: -4.3801

Max Act: 4.1866. Min Act: -0.1700

Data Index: 1803199 (Open Web Text)

Max Activating Token Index: 793

Text #15

Max Range: 4.3801. Min Range: -4.3801

Max Act: 4.1674. Min Act: -0.1700

Data Index: 1295621 (Open Web Text)

Max Activating Token Index: 878

Text #16

Max Range: 4.3801. Min Range: -4.3801

Max Act: 4.1541. Min Act: -0.1700

Data Index: 813592 (Open Web Text)

Max Activating Token Index: 381

Text #17

Max Range: 4.3801. Min Range: -4.3801

Max Act: 4.1249. Min Act: -0.1700

Data Index: 3650323 (Open Web Text)

Max Activating Token Index: 496

Text #18

Max Range: 4.3801. Min Range: -4.3801

Max Act: 4.1288. Min Act: -0.1700

Data Index: 4682843 (Open Web Text)

Max Activating Token Index: 383

Text #19

Max Range: 4.3801. Min Range: -4.3801

Max Act: 4.1266. Min Act: -0.1700

Data Index: 4805388 (Open Web Text)

Max Activating Token Index: 1015