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

Dataset: Open Web Text

Neuron 3033 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: 6.6868. Min Range: -6.6868

Max Act: 6.6868. Min Act: -0.1700

Data Index: 3809876 (Open Web Text)

Max Activating Token Index: 573

Text #1

Max Range: 6.6868. Min Range: -6.6868

Max Act: 6.5702. Min Act: -0.1700

Data Index: 8001109 (Open Web Text)

Max Activating Token Index: 206

Text #2

Max Range: 6.6868. Min Range: -6.6868

Max Act: 6.5120. Min Act: -0.1700

Data Index: 8192952 (Open Web Text)

Max Activating Token Index: 513

Text #3

Max Range: 6.6868. Min Range: -6.6868

Max Act: 6.4326. Min Act: -0.1700

Data Index: 4503272 (Open Web Text)

Max Activating Token Index: 1014

Text #4

Max Range: 6.6868. Min Range: -6.6868

Max Act: 6.4456. Min Act: -0.1700

Data Index: 270315 (Open Web Text)

Max Activating Token Index: 841

Text #5

Max Range: 6.6868. Min Range: -6.6868

Max Act: 6.4529. Min Act: -0.1700

Data Index: 1620306 (Open Web Text)

Max Activating Token Index: 996

Text #6

Max Range: 6.6868. Min Range: -6.6868

Max Act: 6.4181. Min Act: -0.1700

Data Index: 1612940 (Open Web Text)

Max Activating Token Index: 539

Text #7

Max Range: 6.6868. Min Range: -6.6868

Max Act: 6.4059. Min Act: -0.1700

Data Index: 3823316 (Open Web Text)

Max Activating Token Index: 83

Text #8

Max Range: 6.6868. Min Range: -6.6868

Max Act: 6.3287. Min Act: -0.1700

Data Index: 4891290 (Open Web Text)

Max Activating Token Index: 818

Text #9

Max Range: 6.6868. Min Range: -6.6868

Max Act: 6.2875. Min Act: -0.1700

Data Index: 7464853 (Open Web Text)

Max Activating Token Index: 488

Text #10

Max Range: 6.6868. Min Range: -6.6868

Max Act: 6.2600. Min Act: -0.1700

Data Index: 3245476 (Open Web Text)

Max Activating Token Index: 367

Text #11

Max Range: 6.6868. Min Range: -6.6868

Max Act: 6.2865. Min Act: -0.1700

Data Index: 707052 (Open Web Text)

Max Activating Token Index: 499

Text #12

Max Range: 6.6868. Min Range: -6.6868

Max Act: 6.2713. Min Act: -0.1700

Data Index: 7701333 (Open Web Text)

Max Activating Token Index: 1021

Text #13

Max Range: 6.6868. Min Range: -6.6868

Max Act: 6.2829. Min Act: -0.1700

Data Index: 7911167 (Open Web Text)

Max Activating Token Index: 779

Text #14

Max Range: 6.6868. Min Range: -6.6868

Max Act: 6.1596. Min Act: -0.1700

Data Index: 5742066 (Open Web Text)

Max Activating Token Index: 143

Text #15

Max Range: 6.6868. Min Range: -6.6868

Max Act: 6.1507. Min Act: -0.1700

Data Index: 6052534 (Open Web Text)

Max Activating Token Index: 478

Text #16

Max Range: 6.6868. Min Range: -6.6868

Max Act: 6.1680. Min Act: -0.1700

Data Index: 2640208 (Open Web Text)

Max Activating Token Index: 166

Text #17

Max Range: 6.6868. Min Range: -6.6868

Max Act: 6.1701. Min Act: -0.1700

Data Index: 3965530 (Open Web Text)

Max Activating Token Index: 94

Text #18

Max Range: 6.6868. Min Range: -6.6868

Max Act: 6.1957. Min Act: -0.1700

Data Index: 2583953 (Open Web Text)

Max Activating Token Index: 230

Text #19

Max Range: 6.6868. Min Range: -6.6868

Max Act: 6.1446. Min Act: -0.1700

Data Index: 4539289 (Open Web Text)

Max Activating Token Index: 234