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

Dataset: Open Web Text

Neuron 264 in Layer 2

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: 1.7746. Min Range: -1.7746

Max Act: 1.7746. Min Act: -0.1700

Data Index: 6477612 (Open Web Text)

Max Activating Token Index: 79

Text #1

Max Range: 1.7746. Min Range: -1.7746

Max Act: 1.7448. Min Act: -0.1700

Data Index: 3128897 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 1.7746. Min Range: -1.7746

Max Act: 1.7315. Min Act: -0.1699

Data Index: 1105554 (Open Web Text)

Max Activating Token Index: 294

Text #3

Max Range: 1.7746. Min Range: -1.7746

Max Act: 1.7171. Min Act: -0.1700

Data Index: 3142038 (Open Web Text)

Max Activating Token Index: 335

Text #4

Max Range: 1.7746. Min Range: -1.7746

Max Act: 1.7175. Min Act: -0.1700

Data Index: 1089673 (Open Web Text)

Max Activating Token Index: 65

Text #5

Max Range: 1.7746. Min Range: -1.7746

Max Act: 1.7082. Min Act: -0.1700

Data Index: 5808895 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 1.7746. Min Range: -1.7746

Max Act: 1.6972. Min Act: -0.1700

Data Index: 3607330 (Open Web Text)

Max Activating Token Index: 11

Text #7

Max Range: 1.7746. Min Range: -1.7746

Max Act: 1.6951. Min Act: -0.1700

Data Index: 4207666 (Open Web Text)

Max Activating Token Index: 35

Text #8

Max Range: 1.7746. Min Range: -1.7746

Max Act: 1.7137. Min Act: -0.1700

Data Index: 6592284 (Open Web Text)

Max Activating Token Index: 405

Text #9

Max Range: 1.7746. Min Range: -1.7746

Max Act: 1.6896. Min Act: -0.1700

Data Index: 6963187 (Open Web Text)

Max Activating Token Index: 9

Text #10

Max Range: 1.7746. Min Range: -1.7746

Max Act: 1.6785. Min Act: -0.1700

Data Index: 4780285 (Open Web Text)

Max Activating Token Index: 24

Text #11

Max Range: 1.7746. Min Range: -1.7746

Max Act: 1.6698. Min Act: -0.1700

Data Index: 4067506 (Open Web Text)

Max Activating Token Index: 830

Text #12

Max Range: 1.7746. Min Range: -1.7746

Max Act: 1.6688. Min Act: -0.1700

Data Index: 6191175 (Open Web Text)

Max Activating Token Index: 12

Text #13

Max Range: 1.7746. Min Range: -1.7746

Max Act: 1.6661. Min Act: -0.1700

Data Index: 394510 (Open Web Text)

Max Activating Token Index: 225

Text #14

Max Range: 1.7746. Min Range: -1.7746

Max Act: 1.6497. Min Act: -0.1700

Data Index: 6534123 (Open Web Text)

Max Activating Token Index: 241

Text #15

Max Range: 1.7746. Min Range: -1.7746

Max Act: 1.6558. Min Act: -0.1700

Data Index: 2939958 (Open Web Text)

Max Activating Token Index: 290

Text #16

Max Range: 1.7746. Min Range: -1.7746

Max Act: 1.6571. Min Act: -0.1700

Data Index: 3786298 (Open Web Text)

Max Activating Token Index: 22

Text #17

Max Range: 1.7746. Min Range: -1.7746

Max Act: 1.6550. Min Act: -0.1700

Data Index: 2853971 (Open Web Text)

Max Activating Token Index: 557

Text #18

Max Range: 1.7746. Min Range: -1.7746

Max Act: 1.6674. Min Act: -0.1700

Data Index: 2143271 (Open Web Text)

Max Activating Token Index: 990

Text #19

Max Range: 1.7746. Min Range: -1.7746

Max Act: 1.6495. Min Act: -0.1700

Data Index: 2634811 (Open Web Text)

Max Activating Token Index: 9