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

Dataset: Open Web Text

Neuron 1570 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: 3.7508. Min Range: -3.7508

Max Act: 3.7508. Min Act: -0.1700

Data Index: 122357 (Open Web Text)

Max Activating Token Index: 797

Text #1

Max Range: 3.7508. Min Range: -3.7508

Max Act: 3.6717. Min Act: -0.1700

Data Index: 4605196 (Open Web Text)

Max Activating Token Index: 846

Text #2

Max Range: 3.7508. Min Range: -3.7508

Max Act: 3.6200. Min Act: -0.1700

Data Index: 8550827 (Open Web Text)

Max Activating Token Index: 611

Text #3

Max Range: 3.7508. Min Range: -3.7508

Max Act: 3.5901. Min Act: -0.1700

Data Index: 5815810 (Open Web Text)

Max Activating Token Index: 180

Text #4

Max Range: 3.7508. Min Range: -3.7508

Max Act: 3.5816. Min Act: -0.1700

Data Index: 7516829 (Open Web Text)

Max Activating Token Index: 519

Text #5

Max Range: 3.7508. Min Range: -3.7508

Max Act: 3.5335. Min Act: -0.1700

Data Index: 8530936 (Open Web Text)

Max Activating Token Index: 479

Text #6

Max Range: 3.7508. Min Range: -3.7508

Max Act: 3.5261. Min Act: -0.1700

Data Index: 1447260 (Open Web Text)

Max Activating Token Index: 594

Text #7

Max Range: 3.7508. Min Range: -3.7508

Max Act: 3.4758. Min Act: -0.1700

Data Index: 4130689 (Open Web Text)

Max Activating Token Index: 366

Text #8

Max Range: 3.7508. Min Range: -3.7508

Max Act: 3.4756. Min Act: -0.1700

Data Index: 4727351 (Open Web Text)

Max Activating Token Index: 309

Text #9

Max Range: 3.7508. Min Range: -3.7508

Max Act: 3.4547. Min Act: -0.1700

Data Index: 6331635 (Open Web Text)

Max Activating Token Index: 709

Text #10

Max Range: 3.7508. Min Range: -3.7508

Max Act: 3.4977. Min Act: -0.1700

Data Index: 7212226 (Open Web Text)

Max Activating Token Index: 893

Text #11

Max Range: 3.7508. Min Range: -3.7508

Max Act: 3.4168. Min Act: -0.1700

Data Index: 4638911 (Open Web Text)

Max Activating Token Index: 688

Text #12

Max Range: 3.7508. Min Range: -3.7508

Max Act: 3.4664. Min Act: -0.1700

Data Index: 1469651 (Open Web Text)

Max Activating Token Index: 297

Text #13

Max Range: 3.7508. Min Range: -3.7508

Max Act: 3.4639. Min Act: -0.1700

Data Index: 5863545 (Open Web Text)

Max Activating Token Index: 972

Text #14

Max Range: 3.7508. Min Range: -3.7508

Max Act: 3.4630. Min Act: -0.1700

Data Index: 6751739 (Open Web Text)

Max Activating Token Index: 656

Text #15

Max Range: 3.7508. Min Range: -3.7508

Max Act: 3.4598. Min Act: -0.1700

Data Index: 6989429 (Open Web Text)

Max Activating Token Index: 515

Text #16

Max Range: 3.7508. Min Range: -3.7508

Max Act: 3.4338. Min Act: -0.1700

Data Index: 176137 (Open Web Text)

Max Activating Token Index: 485

Text #17

Max Range: 3.7508. Min Range: -3.7508

Max Act: 3.3745. Min Act: -0.1700

Data Index: 5796972 (Open Web Text)

Max Activating Token Index: 496

Text #18

Max Range: 3.7508. Min Range: -3.7508

Max Act: 3.3706. Min Act: -0.1700

Data Index: 1596040 (Open Web Text)

Max Activating Token Index: 299

Text #19

Max Range: 3.7508. Min Range: -3.7508

Max Act: 3.3982. Min Act: -0.1700

Data Index: 6504589 (Open Web Text)

Max Activating Token Index: 329