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

Dataset: Open Web Text

Neuron 416 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: 3.8465. Min Range: -3.8465

Max Act: 3.8465. Min Act: -0.1700

Data Index: 1612823 (Open Web Text)

Max Activating Token Index: 682

Text #1

Max Range: 3.8465. Min Range: -3.8465

Max Act: 3.8205. Min Act: -0.1700

Data Index: 7511965 (Open Web Text)

Max Activating Token Index: 825

Text #2

Max Range: 3.8465. Min Range: -3.8465

Max Act: 3.7970. Min Act: -0.1700

Data Index: 4415365 (Open Web Text)

Max Activating Token Index: 403

Text #3

Max Range: 3.8465. Min Range: -3.8465

Max Act: 3.7906. Min Act: -0.1700

Data Index: 1612817 (Open Web Text)

Max Activating Token Index: 477

Text #4

Max Range: 3.8465. Min Range: -3.8465

Max Act: 3.7645. Min Act: -0.1700

Data Index: 5099925 (Open Web Text)

Max Activating Token Index: 442

Text #5

Max Range: 3.8465. Min Range: -3.8465

Max Act: 3.7623. Min Act: -0.1700

Data Index: 3674987 (Open Web Text)

Max Activating Token Index: 610

Text #6

Max Range: 3.8465. Min Range: -3.8465

Max Act: 3.7474. Min Act: -0.1700

Data Index: 4480798 (Open Web Text)

Max Activating Token Index: 459

Text #7

Max Range: 3.8465. Min Range: -3.8465

Max Act: 3.7131. Min Act: -0.1700

Data Index: 2571555 (Open Web Text)

Max Activating Token Index: 519

Text #8

Max Range: 3.8465. Min Range: -3.8465

Max Act: 3.7229. Min Act: -0.1700

Data Index: 3653841 (Open Web Text)

Max Activating Token Index: 174

Text #9

Max Range: 3.8465. Min Range: -3.8465

Max Act: 3.7321. Min Act: -0.1700

Data Index: 1216753 (Open Web Text)

Max Activating Token Index: 569

Text #10

Max Range: 3.8465. Min Range: -3.8465

Max Act: 3.7206. Min Act: -0.1700

Data Index: 3527536 (Open Web Text)

Max Activating Token Index: 767

Text #11

Max Range: 3.8465. Min Range: -3.8465

Max Act: 3.7436. Min Act: -0.1700

Data Index: 3485442 (Open Web Text)

Max Activating Token Index: 288

Text #12

Max Range: 3.8465. Min Range: -3.8465

Max Act: 3.7248. Min Act: -0.1700

Data Index: 8332118 (Open Web Text)

Max Activating Token Index: 627

Text #13

Max Range: 3.8465. Min Range: -3.8465

Max Act: 3.7144. Min Act: -0.1700

Data Index: 3099205 (Open Web Text)

Max Activating Token Index: 516

Text #14

Max Range: 3.8465. Min Range: -3.8465

Max Act: 3.7158. Min Act: -0.1700

Data Index: 3361004 (Open Web Text)

Max Activating Token Index: 473

Text #15

Max Range: 3.8465. Min Range: -3.8465

Max Act: 3.7058. Min Act: -0.1700

Data Index: 1617562 (Open Web Text)

Max Activating Token Index: 643

Text #16

Max Range: 3.8465. Min Range: -3.8465

Max Act: 3.6817. Min Act: -0.1700

Data Index: 747168 (Open Web Text)

Max Activating Token Index: 503

Text #17

Max Range: 3.8465. Min Range: -3.8465

Max Act: 3.6864. Min Act: -0.1700

Data Index: 2051232 (Open Web Text)

Max Activating Token Index: 153

Text #18

Max Range: 3.8465. Min Range: -3.8465

Max Act: 3.7158. Min Act: -0.1700

Data Index: 2137289 (Open Web Text)

Max Activating Token Index: 657

Text #19

Max Range: 3.8465. Min Range: -3.8465

Max Act: 3.6922. Min Act: -0.1700

Data Index: 1150379 (Open Web Text)

Max Activating Token Index: 523