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

Dataset: Open Web Text

Neuron 2107 in Layer 3

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: 3.5714. Min Range: -3.5714

Max Act: 3.5714. Min Act: -0.1700

Data Index: 1132607 (Open Web Text)

Max Activating Token Index: 38

Text #1

Max Range: 3.5714. Min Range: -3.5714

Max Act: 3.5574. Min Act: -0.1700

Data Index: 8126095 (Open Web Text)

Max Activating Token Index: 278

Text #2

Max Range: 3.5714. Min Range: -3.5714

Max Act: 3.4684. Min Act: -0.1700

Data Index: 6116862 (Open Web Text)

Max Activating Token Index: 582

Text #3

Max Range: 3.5714. Min Range: -3.5714

Max Act: 3.4695. Min Act: -0.1700

Data Index: 8184650 (Open Web Text)

Max Activating Token Index: 396

Text #4

Max Range: 3.5714. Min Range: -3.5714

Max Act: 3.4196. Min Act: -0.1700

Data Index: 7140245 (Open Web Text)

Max Activating Token Index: 179

Text #5

Max Range: 3.5714. Min Range: -3.5714

Max Act: 3.4503. Min Act: -0.1700

Data Index: 2933535 (Open Web Text)

Max Activating Token Index: 982

Text #6

Max Range: 3.5714. Min Range: -3.5714

Max Act: 3.4546. Min Act: -0.1700

Data Index: 5756020 (Open Web Text)

Max Activating Token Index: 438

Text #7

Max Range: 3.5714. Min Range: -3.5714

Max Act: 3.4169. Min Act: -0.1700

Data Index: 6257960 (Open Web Text)

Max Activating Token Index: 941

Text #8

Max Range: 3.5714. Min Range: -3.5714

Max Act: 3.4189. Min Act: -0.1700

Data Index: 7048624 (Open Web Text)

Max Activating Token Index: 607

Text #9

Max Range: 3.5714. Min Range: -3.5714

Max Act: 3.4159. Min Act: -0.1700

Data Index: 2340872 (Open Web Text)

Max Activating Token Index: 975

Text #10

Max Range: 3.5714. Min Range: -3.5714

Max Act: 3.4072. Min Act: -0.1700

Data Index: 8174282 (Open Web Text)

Max Activating Token Index: 102

Text #11

Max Range: 3.5714. Min Range: -3.5714

Max Act: 3.4223. Min Act: -0.1700

Data Index: 8136522 (Open Web Text)

Max Activating Token Index: 784

Text #12

Max Range: 3.5714. Min Range: -3.5714

Max Act: 3.3979. Min Act: -0.1700

Data Index: 7140251 (Open Web Text)

Max Activating Token Index: 637

Text #13

Max Range: 3.5714. Min Range: -3.5714

Max Act: 3.4063. Min Act: -0.1700

Data Index: 4828793 (Open Web Text)

Max Activating Token Index: 995

Text #14

Max Range: 3.5714. Min Range: -3.5714

Max Act: 3.3997. Min Act: -0.1700

Data Index: 6617638 (Open Web Text)

Max Activating Token Index: 581

Text #15

Max Range: 3.5714. Min Range: -3.5714

Max Act: 3.3818. Min Act: -0.1700

Data Index: 5387729 (Open Web Text)

Max Activating Token Index: 873

Text #16

Max Range: 3.5714. Min Range: -3.5714

Max Act: 3.4022. Min Act: -0.1700

Data Index: 6159507 (Open Web Text)

Max Activating Token Index: 112

Text #17

Max Range: 3.5714. Min Range: -3.5714

Max Act: 3.4037. Min Act: -0.1700

Data Index: 4773122 (Open Web Text)

Max Activating Token Index: 863

Text #18

Max Range: 3.5714. Min Range: -3.5714

Max Act: 3.3662. Min Act: -0.1700

Data Index: 142068 (Open Web Text)

Max Activating Token Index: 880

Text #19

Max Range: 3.5714. Min Range: -3.5714

Max Act: 3.3900. Min Act: -0.1700

Data Index: 5573179 (Open Web Text)

Max Activating Token Index: 970