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

Dataset: Open Web Text

Neuron 2000 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: 3.4095. Min Range: -3.4095

Max Act: 3.4095. Min Act: -0.1700

Data Index: 5265549 (Open Web Text)

Max Activating Token Index: 882

Text #1

Max Range: 3.4095. Min Range: -3.4095

Max Act: 3.3844. Min Act: -0.1700

Data Index: 1381520 (Open Web Text)

Max Activating Token Index: 510

Text #2

Max Range: 3.4095. Min Range: -3.4095

Max Act: 3.3468. Min Act: -0.1700

Data Index: 8472420 (Open Web Text)

Max Activating Token Index: 450

Text #3

Max Range: 3.4095. Min Range: -3.4095

Max Act: 3.3366. Min Act: -0.1700

Data Index: 1279826 (Open Web Text)

Max Activating Token Index: 243

Text #4

Max Range: 3.4095. Min Range: -3.4095

Max Act: 3.3149. Min Act: -0.1700

Data Index: 4240399 (Open Web Text)

Max Activating Token Index: 540

Text #5

Max Range: 3.4095. Min Range: -3.4095

Max Act: 3.3176. Min Act: -0.1700

Data Index: 1167195 (Open Web Text)

Max Activating Token Index: 921

Text #6

Max Range: 3.4095. Min Range: -3.4095

Max Act: 3.3071. Min Act: -0.1700

Data Index: 4344056 (Open Web Text)

Max Activating Token Index: 511

Text #7

Max Range: 3.4095. Min Range: -3.4095

Max Act: 3.2920. Min Act: -0.1700

Data Index: 457753 (Open Web Text)

Max Activating Token Index: 404

Text #8

Max Range: 3.4095. Min Range: -3.4095

Max Act: 3.2718. Min Act: -0.1700

Data Index: 7826680 (Open Web Text)

Max Activating Token Index: 790

Text #9

Max Range: 3.4095. Min Range: -3.4095

Max Act: 3.2629. Min Act: -0.1700

Data Index: 482060 (Open Web Text)

Max Activating Token Index: 506

Text #10

Max Range: 3.4095. Min Range: -3.4095

Max Act: 3.2575. Min Act: -0.1700

Data Index: 6024697 (Open Web Text)

Max Activating Token Index: 376

Text #11

Max Range: 3.4095. Min Range: -3.4095

Max Act: 3.2510. Min Act: -0.1700

Data Index: 6793263 (Open Web Text)

Max Activating Token Index: 893

Text #12

Max Range: 3.4095. Min Range: -3.4095

Max Act: 3.2691. Min Act: -0.1700

Data Index: 2938080 (Open Web Text)

Max Activating Token Index: 726

Text #13

Max Range: 3.4095. Min Range: -3.4095

Max Act: 3.2736. Min Act: -0.1700

Data Index: 4824531 (Open Web Text)

Max Activating Token Index: 494

Text #14

Max Range: 3.4095. Min Range: -3.4095

Max Act: 3.2619. Min Act: -0.1700

Data Index: 1389315 (Open Web Text)

Max Activating Token Index: 920

Text #15

Max Range: 3.4095. Min Range: -3.4095

Max Act: 3.2385. Min Act: -0.1700

Data Index: 4159826 (Open Web Text)

Max Activating Token Index: 321

Text #16

Max Range: 3.4095. Min Range: -3.4095

Max Act: 3.2196. Min Act: -0.1700

Data Index: 2023153 (Open Web Text)

Max Activating Token Index: 795

Text #17

Max Range: 3.4095. Min Range: -3.4095

Max Act: 3.2439. Min Act: -0.1700

Data Index: 8761836 (Open Web Text)

Max Activating Token Index: 192

Text #18

Max Range: 3.4095. Min Range: -3.4095

Max Act: 3.2458. Min Act: -0.1700

Data Index: 2362191 (Open Web Text)

Max Activating Token Index: 734

Text #19

Max Range: 3.4095. Min Range: -3.4095

Max Act: 3.2384. Min Act: -0.1700

Data Index: 4236741 (Open Web Text)

Max Activating Token Index: 268