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

Dataset: Open Web Text

Neuron 340 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: 4.0435. Min Range: -4.0435

Max Act: 4.0179. Min Act: -0.1700

Data Index: 2055328 (Open Web Text)

Max Activating Token Index: 451

Text #1

Max Range: 4.0435. Min Range: -4.0435

Max Act: 4.0435. Min Act: -0.1700

Data Index: 1635577 (Open Web Text)

Max Activating Token Index: 898

Text #2

Max Range: 4.0435. Min Range: -4.0435

Max Act: 3.9742. Min Act: -0.1700

Data Index: 3552962 (Open Web Text)

Max Activating Token Index: 582

Text #3

Max Range: 4.0435. Min Range: -4.0435

Max Act: 4.0390. Min Act: -0.1700

Data Index: 3076847 (Open Web Text)

Max Activating Token Index: 69

Text #4

Max Range: 4.0435. Min Range: -4.0435

Max Act: 3.9854. Min Act: -0.1700

Data Index: 3456238 (Open Web Text)

Max Activating Token Index: 601

Text #5

Max Range: 4.0435. Min Range: -4.0435

Max Act: 3.9438. Min Act: -0.1700

Data Index: 7168679 (Open Web Text)

Max Activating Token Index: 539

Text #6

Max Range: 4.0435. Min Range: -4.0435

Max Act: 3.9317. Min Act: -0.1700

Data Index: 1561035 (Open Web Text)

Max Activating Token Index: 812

Text #7

Max Range: 4.0435. Min Range: -4.0435

Max Act: 3.9307. Min Act: -0.1700

Data Index: 2888948 (Open Web Text)

Max Activating Token Index: 665

Text #8

Max Range: 4.0435. Min Range: -4.0435

Max Act: 3.9154. Min Act: -0.1700

Data Index: 1894526 (Open Web Text)

Max Activating Token Index: 191

Text #9

Max Range: 4.0435. Min Range: -4.0435

Max Act: 3.8939. Min Act: -0.1700

Data Index: 3359197 (Open Web Text)

Max Activating Token Index: 340

Text #10

Max Range: 4.0435. Min Range: -4.0435

Max Act: 3.9193. Min Act: -0.1700

Data Index: 4200288 (Open Web Text)

Max Activating Token Index: 477

Text #11

Max Range: 4.0435. Min Range: -4.0435

Max Act: 3.9030. Min Act: -0.1700

Data Index: 5521823 (Open Web Text)

Max Activating Token Index: 435

Text #12

Max Range: 4.0435. Min Range: -4.0435

Max Act: 3.8622. Min Act: -0.1700

Data Index: 8330306 (Open Web Text)

Max Activating Token Index: 531

Text #13

Max Range: 4.0435. Min Range: -4.0435

Max Act: 3.8689. Min Act: -0.1700

Data Index: 8471816 (Open Web Text)

Max Activating Token Index: 462

Text #14

Max Range: 4.0435. Min Range: -4.0435

Max Act: 3.8864. Min Act: -0.1700

Data Index: 3884057 (Open Web Text)

Max Activating Token Index: 827

Text #15

Max Range: 4.0435. Min Range: -4.0435

Max Act: 3.8770. Min Act: -0.1700

Data Index: 3874924 (Open Web Text)

Max Activating Token Index: 586

Text #16

Max Range: 4.0435. Min Range: -4.0435

Max Act: 3.8735. Min Act: -0.1700

Data Index: 5195112 (Open Web Text)

Max Activating Token Index: 87

Text #17

Max Range: 4.0435. Min Range: -4.0435

Max Act: 3.8591. Min Act: -0.1700

Data Index: 3649089 (Open Web Text)

Max Activating Token Index: 322

Text #18

Max Range: 4.0435. Min Range: -4.0435

Max Act: 3.8267. Min Act: -0.1700

Data Index: 3181915 (Open Web Text)

Max Activating Token Index: 148

Text #19

Max Range: 4.0435. Min Range: -4.0435

Max Act: 3.8428. Min Act: -0.1700

Data Index: 410809 (Open Web Text)

Max Activating Token Index: 187