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

Dataset: Open Web Text

Neuron 2027 in Layer 6

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: 6.3695. Min Range: -6.3695

Max Act: 6.3695. Min Act: -0.1700

Data Index: 3019552 (Open Web Text)

Max Activating Token Index: 724

Text #1

Max Range: 6.3695. Min Range: -6.3695

Max Act: 6.2692. Min Act: -0.1700

Data Index: 6824983 (Open Web Text)

Max Activating Token Index: 787

Text #2

Max Range: 6.3695. Min Range: -6.3695

Max Act: 6.1146. Min Act: -0.1700

Data Index: 52112 (Open Web Text)

Max Activating Token Index: 412

Text #3

Max Range: 6.3695. Min Range: -6.3695

Max Act: 6.0350. Min Act: -0.1700

Data Index: 3980137 (Open Web Text)

Max Activating Token Index: 539

Text #4

Max Range: 6.3695. Min Range: -6.3695

Max Act: 5.9595. Min Act: -0.1700

Data Index: 388747 (Open Web Text)

Max Activating Token Index: 628

Text #5

Max Range: 6.3695. Min Range: -6.3695

Max Act: 5.9666. Min Act: -0.1700

Data Index: 1926550 (Open Web Text)

Max Activating Token Index: 389

Text #6

Max Range: 6.3695. Min Range: -6.3695

Max Act: 5.9243. Min Act: -0.1700

Data Index: 5163951 (Open Web Text)

Max Activating Token Index: 399

Text #7

Max Range: 6.3695. Min Range: -6.3695

Max Act: 5.8667. Min Act: -0.1700

Data Index: 8650030 (Open Web Text)

Max Activating Token Index: 362

Text #8

Max Range: 6.3695. Min Range: -6.3695

Max Act: 5.8304. Min Act: -0.1700

Data Index: 8716970 (Open Web Text)

Max Activating Token Index: 877

Text #9

Max Range: 6.3695. Min Range: -6.3695

Max Act: 5.7443. Min Act: -0.1700

Data Index: 1636448 (Open Web Text)

Max Activating Token Index: 674

Text #10

Max Range: 6.3695. Min Range: -6.3695

Max Act: 5.7948. Min Act: -0.1700

Data Index: 5625662 (Open Web Text)

Max Activating Token Index: 761

Text #11

Max Range: 6.3695. Min Range: -6.3695

Max Act: 5.7290. Min Act: -0.1700

Data Index: 1203682 (Open Web Text)

Max Activating Token Index: 652

Text #12

Max Range: 6.3695. Min Range: -6.3695

Max Act: 5.7424. Min Act: -0.1700

Data Index: 3611413 (Open Web Text)

Max Activating Token Index: 480

Text #13

Max Range: 6.3695. Min Range: -6.3695

Max Act: 5.7365. Min Act: -0.1700

Data Index: 83775 (Open Web Text)

Max Activating Token Index: 867

Text #14

Max Range: 6.3695. Min Range: -6.3695

Max Act: 5.8091. Min Act: -0.1700

Data Index: 2277486 (Open Web Text)

Max Activating Token Index: 471

Text #15

Max Range: 6.3695. Min Range: -6.3695

Max Act: 5.7323. Min Act: -0.1700

Data Index: 7465178 (Open Web Text)

Max Activating Token Index: 470

Text #16

Max Range: 6.3695. Min Range: -6.3695

Max Act: 5.7367. Min Act: -0.1700

Data Index: 5488912 (Open Web Text)

Max Activating Token Index: 919

Text #17

Max Range: 6.3695. Min Range: -6.3695

Max Act: 5.7203. Min Act: -0.1700

Data Index: 3716246 (Open Web Text)

Max Activating Token Index: 882

Text #18

Max Range: 6.3695. Min Range: -6.3695

Max Act: 5.7182. Min Act: -0.1700

Data Index: 8472283 (Open Web Text)

Max Activating Token Index: 656

Text #19

Max Range: 6.3695. Min Range: -6.3695

Max Act: 5.7495. Min Act: -0.1700

Data Index: 3050524 (Open Web Text)

Max Activating Token Index: 751