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

Dataset: Open Web Text

Neuron 2493 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: 3.6149. Min Range: -3.6149

Max Act: 3.6149. Min Act: -0.1700

Data Index: 1072278 (Open Web Text)

Max Activating Token Index: 35

Text #1

Max Range: 3.6149. Min Range: -3.6149

Max Act: 3.5125. Min Act: -0.1700

Data Index: 6189243 (Open Web Text)

Max Activating Token Index: 38

Text #2

Max Range: 3.6149. Min Range: -3.6149

Max Act: 3.4657. Min Act: -0.1700

Data Index: 2110364 (Open Web Text)

Max Activating Token Index: 507

Text #3

Max Range: 3.6149. Min Range: -3.6149

Max Act: 3.4581. Min Act: -0.1700

Data Index: 7292798 (Open Web Text)

Max Activating Token Index: 80

Text #4

Max Range: 3.6149. Min Range: -3.6149

Max Act: 3.4203. Min Act: -0.1700

Data Index: 610742 (Open Web Text)

Max Activating Token Index: 839

Text #5

Max Range: 3.6149. Min Range: -3.6149

Max Act: 3.4267. Min Act: -0.1700

Data Index: 4980088 (Open Web Text)

Max Activating Token Index: 89

Text #6

Max Range: 3.6149. Min Range: -3.6149

Max Act: 3.4048. Min Act: -0.1700

Data Index: 2231107 (Open Web Text)

Max Activating Token Index: 900

Text #7

Max Range: 3.6149. Min Range: -3.6149

Max Act: 3.3646. Min Act: -0.1700

Data Index: 3976084 (Open Web Text)

Max Activating Token Index: 594

Text #8

Max Range: 3.6149. Min Range: -3.6149

Max Act: 3.3923. Min Act: -0.1700

Data Index: 8023744 (Open Web Text)

Max Activating Token Index: 24

Text #9

Max Range: 3.6149. Min Range: -3.6149

Max Act: 3.3616. Min Act: -0.1700

Data Index: 6971972 (Open Web Text)

Max Activating Token Index: 477

Text #10

Max Range: 3.6149. Min Range: -3.6149

Max Act: 3.3760. Min Act: -0.1700

Data Index: 3224696 (Open Web Text)

Max Activating Token Index: 108

Text #11

Max Range: 3.6149. Min Range: -3.6149

Max Act: 3.3808. Min Act: -0.1700

Data Index: 6297954 (Open Web Text)

Max Activating Token Index: 872

Text #12

Max Range: 3.6149. Min Range: -3.6149

Max Act: 3.3378. Min Act: -0.1700

Data Index: 7955808 (Open Web Text)

Max Activating Token Index: 345

Text #13

Max Range: 3.6149. Min Range: -3.6149

Max Act: 3.3456. Min Act: -0.1700

Data Index: 3208583 (Open Web Text)

Max Activating Token Index: 108

Text #14

Max Range: 3.6149. Min Range: -3.6149

Max Act: 3.3405. Min Act: -0.1700

Data Index: 1592604 (Open Web Text)

Max Activating Token Index: 862

Text #15

Max Range: 3.6149. Min Range: -3.6149

Max Act: 3.3115. Min Act: -0.1700

Data Index: 1022212 (Open Web Text)

Max Activating Token Index: 591

Text #16

Max Range: 3.6149. Min Range: -3.6149

Max Act: 3.3443. Min Act: -0.1700

Data Index: 7070326 (Open Web Text)

Max Activating Token Index: 997

Text #17

Max Range: 3.6149. Min Range: -3.6149

Max Act: 3.3187. Min Act: -0.1700

Data Index: 4641863 (Open Web Text)

Max Activating Token Index: 104

Text #18

Max Range: 3.6149. Min Range: -3.6149

Max Act: 3.3078. Min Act: -0.1700

Data Index: 7933428 (Open Web Text)

Max Activating Token Index: 108

Text #19

Max Range: 3.6149. Min Range: -3.6149

Max Act: 3.2962. Min Act: -0.1700

Data Index: 348745 (Open Web Text)

Max Activating Token Index: 644