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

Dataset: Open Web Text

Neuron 2189 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: 3.1656. Min Range: -3.1656

Max Act: 3.1656. Min Act: -0.1700

Data Index: 5587974 (Open Web Text)

Max Activating Token Index: 669

Text #1

Max Range: 3.1656. Min Range: -3.1656

Max Act: 3.0610. Min Act: -0.1700

Data Index: 2990198 (Open Web Text)

Max Activating Token Index: 653

Text #2

Max Range: 3.1656. Min Range: -3.1656

Max Act: 2.9980. Min Act: -0.1700

Data Index: 4648413 (Open Web Text)

Max Activating Token Index: 78

Text #3

Max Range: 3.1656. Min Range: -3.1656

Max Act: 2.9848. Min Act: -0.1700

Data Index: 6453904 (Open Web Text)

Max Activating Token Index: 891

Text #4

Max Range: 3.1656. Min Range: -3.1656

Max Act: 2.9053. Min Act: -0.1700

Data Index: 1715178 (Open Web Text)

Max Activating Token Index: 579

Text #5

Max Range: 3.1656. Min Range: -3.1656

Max Act: 2.8812. Min Act: -0.1700

Data Index: 8187206 (Open Web Text)

Max Activating Token Index: 901

Text #6

Max Range: 3.1656. Min Range: -3.1656

Max Act: 2.9031. Min Act: -0.1700

Data Index: 686989 (Open Web Text)

Max Activating Token Index: 990

Text #7

Max Range: 3.1656. Min Range: -3.1656

Max Act: 2.9113. Min Act: -0.1700

Data Index: 1980456 (Open Web Text)

Max Activating Token Index: 669

Text #8

Max Range: 3.1656. Min Range: -3.1656

Max Act: 2.8987. Min Act: -0.1700

Data Index: 2255327 (Open Web Text)

Max Activating Token Index: 641

Text #9

Max Range: 3.1656. Min Range: -3.1656

Max Act: 2.8528. Min Act: -0.1700

Data Index: 7973301 (Open Web Text)

Max Activating Token Index: 364

Text #10

Max Range: 3.1656. Min Range: -3.1656

Max Act: 2.8625. Min Act: -0.1700

Data Index: 8668091 (Open Web Text)

Max Activating Token Index: 849

Text #11

Max Range: 3.1656. Min Range: -3.1656

Max Act: 2.8377. Min Act: -0.1700

Data Index: 3490130 (Open Web Text)

Max Activating Token Index: 687

Text #12

Max Range: 3.1656. Min Range: -3.1656

Max Act: 2.8321. Min Act: -0.1700

Data Index: 1280317 (Open Web Text)

Max Activating Token Index: 722

Text #13

Max Range: 3.1656. Min Range: -3.1656

Max Act: 2.8310. Min Act: -0.1700

Data Index: 8197096 (Open Web Text)

Max Activating Token Index: 134

Text #14

Max Range: 3.1656. Min Range: -3.1656

Max Act: 2.8383. Min Act: -0.1700

Data Index: 163800 (Open Web Text)

Max Activating Token Index: 813

Text #15

Max Range: 3.1656. Min Range: -3.1656

Max Act: 2.8319. Min Act: -0.1700

Data Index: 6331128 (Open Web Text)

Max Activating Token Index: 171

Text #16

Max Range: 3.1656. Min Range: -3.1656

Max Act: 2.8444. Min Act: -0.1700

Data Index: 6875911 (Open Web Text)

Max Activating Token Index: 155

Text #17

Max Range: 3.1656. Min Range: -3.1656

Max Act: 2.8170. Min Act: -0.1700

Data Index: 4970028 (Open Web Text)

Max Activating Token Index: 737

Text #18

Max Range: 3.1656. Min Range: -3.1656

Max Act: 2.8268. Min Act: -0.1700

Data Index: 8668145 (Open Web Text)

Max Activating Token Index: 83

Text #19

Max Range: 3.1656. Min Range: -3.1656

Max Act: 2.8173. Min Act: -0.1700

Data Index: 7368810 (Open Web Text)

Max Activating Token Index: 122