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

Dataset: Open Web Text

Neuron 2360 in Layer 5

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: 6.0763. Min Range: -6.0763

Max Act: 6.0763. Min Act: -0.1700

Data Index: 5142589 (Open Web Text)

Max Activating Token Index: 230

Text #1

Max Range: 6.0763. Min Range: -6.0763

Max Act: 5.6675. Min Act: -0.1700

Data Index: 7832543 (Open Web Text)

Max Activating Token Index: 77

Text #2

Max Range: 6.0763. Min Range: -6.0763

Max Act: 5.6571. Min Act: -0.1700

Data Index: 3185285 (Open Web Text)

Max Activating Token Index: 572

Text #3

Max Range: 6.0763. Min Range: -6.0763

Max Act: 5.6481. Min Act: -0.1700

Data Index: 7115680 (Open Web Text)

Max Activating Token Index: 355

Text #4

Max Range: 6.0763. Min Range: -6.0763

Max Act: 5.6061. Min Act: -0.1700

Data Index: 2847317 (Open Web Text)

Max Activating Token Index: 189

Text #5

Max Range: 6.0763. Min Range: -6.0763

Max Act: 5.6039. Min Act: -0.1700

Data Index: 2741933 (Open Web Text)

Max Activating Token Index: 555

Text #6

Max Range: 6.0763. Min Range: -6.0763

Max Act: 5.5389. Min Act: -0.1700

Data Index: 3408909 (Open Web Text)

Max Activating Token Index: 607

Text #7

Max Range: 6.0763. Min Range: -6.0763

Max Act: 5.5101. Min Act: -0.1700

Data Index: 1560055 (Open Web Text)

Max Activating Token Index: 241

Text #8

Max Range: 6.0763. Min Range: -6.0763

Max Act: 5.5014. Min Act: -0.1700

Data Index: 6652334 (Open Web Text)

Max Activating Token Index: 945

Text #9

Max Range: 6.0763. Min Range: -6.0763

Max Act: 5.5117. Min Act: -0.1700

Data Index: 8036230 (Open Web Text)

Max Activating Token Index: 352

Text #10

Max Range: 6.0763. Min Range: -6.0763

Max Act: 5.5151. Min Act: -0.1700

Data Index: 3815064 (Open Web Text)

Max Activating Token Index: 437

Text #11

Max Range: 6.0763. Min Range: -6.0763

Max Act: 5.5398. Min Act: -0.1700

Data Index: 4273709 (Open Web Text)

Max Activating Token Index: 89

Text #12

Max Range: 6.0763. Min Range: -6.0763

Max Act: 5.4738. Min Act: -0.1700

Data Index: 6986455 (Open Web Text)

Max Activating Token Index: 624

Text #13

Max Range: 6.0763. Min Range: -6.0763

Max Act: 5.5103. Min Act: -0.1700

Data Index: 7736117 (Open Web Text)

Max Activating Token Index: 129

Text #14

Max Range: 6.0763. Min Range: -6.0763

Max Act: 5.4766. Min Act: -0.1700

Data Index: 1690088 (Open Web Text)

Max Activating Token Index: 639

Text #15

Max Range: 6.0763. Min Range: -6.0763

Max Act: 5.4571. Min Act: -0.1700

Data Index: 4351864 (Open Web Text)

Max Activating Token Index: 463

Text #16

Max Range: 6.0763. Min Range: -6.0763

Max Act: 5.4495. Min Act: -0.1700

Data Index: 4936818 (Open Web Text)

Max Activating Token Index: 182

Text #17

Max Range: 6.0763. Min Range: -6.0763

Max Act: 5.4588. Min Act: -0.1700

Data Index: 6800572 (Open Web Text)

Max Activating Token Index: 905

Text #18

Max Range: 6.0763. Min Range: -6.0763

Max Act: 5.4738. Min Act: -0.1700

Data Index: 5661144 (Open Web Text)

Max Activating Token Index: 224

Text #19

Max Range: 6.0763. Min Range: -6.0763

Max Act: 5.4465. Min Act: -0.1700

Data Index: 5959539 (Open Web Text)

Max Activating Token Index: 430