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

Dataset: Open Web Text

Neuron 2502 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: 3.7144. Min Range: -3.7144

Max Act: 3.7144. Min Act: -0.1700

Data Index: 6017667 (Open Web Text)

Max Activating Token Index: 960

Text #1

Max Range: 3.7144. Min Range: -3.7144

Max Act: 3.6617. Min Act: -0.1700

Data Index: 4447500 (Open Web Text)

Max Activating Token Index: 363

Text #2

Max Range: 3.7144. Min Range: -3.7144

Max Act: 3.5415. Min Act: -0.1700

Data Index: 5261232 (Open Web Text)

Max Activating Token Index: 335

Text #3

Max Range: 3.7144. Min Range: -3.7144

Max Act: 3.5389. Min Act: -0.1700

Data Index: 8041375 (Open Web Text)

Max Activating Token Index: 355

Text #4

Max Range: 3.7144. Min Range: -3.7144

Max Act: 3.5210. Min Act: -0.1700

Data Index: 3990381 (Open Web Text)

Max Activating Token Index: 726

Text #5

Max Range: 3.7144. Min Range: -3.7144

Max Act: 3.4884. Min Act: -0.1700

Data Index: 3715433 (Open Web Text)

Max Activating Token Index: 141

Text #6

Max Range: 3.7144. Min Range: -3.7144

Max Act: 3.5222. Min Act: -0.1700

Data Index: 8269168 (Open Web Text)

Max Activating Token Index: 701

Text #7

Max Range: 3.7144. Min Range: -3.7144

Max Act: 3.5099. Min Act: -0.1700

Data Index: 7285704 (Open Web Text)

Max Activating Token Index: 897

Text #8

Max Range: 3.7144. Min Range: -3.7144

Max Act: 3.5104. Min Act: -0.1700

Data Index: 7462567 (Open Web Text)

Max Activating Token Index: 544

Text #9

Max Range: 3.7144. Min Range: -3.7144

Max Act: 3.4958. Min Act: -0.1700

Data Index: 2642780 (Open Web Text)

Max Activating Token Index: 309

Text #10

Max Range: 3.7144. Min Range: -3.7144

Max Act: 3.4857. Min Act: -0.1700

Data Index: 5618518 (Open Web Text)

Max Activating Token Index: 714

Text #11

Max Range: 3.7144. Min Range: -3.7144

Max Act: 3.4711. Min Act: -0.1700

Data Index: 4368133 (Open Web Text)

Max Activating Token Index: 647

Text #12

Max Range: 3.7144. Min Range: -3.7144

Max Act: 3.4706. Min Act: -0.1700

Data Index: 4946952 (Open Web Text)

Max Activating Token Index: 984

Text #13

Max Range: 3.7144. Min Range: -3.7144

Max Act: 3.4317. Min Act: -0.1700

Data Index: 543253 (Open Web Text)

Max Activating Token Index: 695

Text #14

Max Range: 3.7144. Min Range: -3.7144

Max Act: 3.4447. Min Act: -0.1700

Data Index: 3857569 (Open Web Text)

Max Activating Token Index: 839

Text #15

Max Range: 3.7144. Min Range: -3.7144

Max Act: 3.3844. Min Act: -0.1700

Data Index: 204290 (Open Web Text)

Max Activating Token Index: 916

Text #16

Max Range: 3.7144. Min Range: -3.7144

Max Act: 3.3982. Min Act: -0.1700

Data Index: 5893194 (Open Web Text)

Max Activating Token Index: 899

Text #17

Max Range: 3.7144. Min Range: -3.7144

Max Act: 3.3908. Min Act: -0.1700

Data Index: 2270579 (Open Web Text)

Max Activating Token Index: 454

Text #18

Max Range: 3.7144. Min Range: -3.7144

Max Act: 3.3658. Min Act: -0.1700

Data Index: 8174532 (Open Web Text)

Max Activating Token Index: 691

Text #19

Max Range: 3.7144. Min Range: -3.7144

Max Act: 3.3662. Min Act: -0.1700

Data Index: 5225515 (Open Web Text)

Max Activating Token Index: 574