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

Dataset: Open Web Text

Neuron 2437 in Layer 3

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: 4.9290. Min Range: -4.9290

Max Act: 4.9290. Min Act: -0.1700

Data Index: 2284030 (Open Web Text)

Max Activating Token Index: 539

Text #1

Max Range: 4.9290. Min Range: -4.9290

Max Act: 4.7927. Min Act: -0.1700

Data Index: 7346035 (Open Web Text)

Max Activating Token Index: 954

Text #2

Max Range: 4.9290. Min Range: -4.9290

Max Act: 4.7168. Min Act: -0.1700

Data Index: 5974611 (Open Web Text)

Max Activating Token Index: 41

Text #3

Max Range: 4.9290. Min Range: -4.9290

Max Act: 4.7025. Min Act: -0.1700

Data Index: 1883741 (Open Web Text)

Max Activating Token Index: 994

Text #4

Max Range: 4.9290. Min Range: -4.9290

Max Act: 4.6875. Min Act: -0.1700

Data Index: 1732333 (Open Web Text)

Max Activating Token Index: 545

Text #5

Max Range: 4.9290. Min Range: -4.9290

Max Act: 4.6875. Min Act: -0.1700

Data Index: 1865530 (Open Web Text)

Max Activating Token Index: 497

Text #6

Max Range: 4.9290. Min Range: -4.9290

Max Act: 4.6874. Min Act: -0.1700

Data Index: 8350056 (Open Web Text)

Max Activating Token Index: 247

Text #7

Max Range: 4.9290. Min Range: -4.9290

Max Act: 4.7150. Min Act: -0.1700

Data Index: 6164854 (Open Web Text)

Max Activating Token Index: 587

Text #8

Max Range: 4.9290. Min Range: -4.9290

Max Act: 4.7087. Min Act: -0.1700

Data Index: 5066922 (Open Web Text)

Max Activating Token Index: 48

Text #9

Max Range: 4.9290. Min Range: -4.9290

Max Act: 4.6565. Min Act: -0.1700

Data Index: 3126981 (Open Web Text)

Max Activating Token Index: 542

Text #10

Max Range: 4.9290. Min Range: -4.9290

Max Act: 4.6420. Min Act: -0.1700

Data Index: 3362166 (Open Web Text)

Max Activating Token Index: 132

Text #11

Max Range: 4.9290. Min Range: -4.9290

Max Act: 4.6864. Min Act: -0.1700

Data Index: 8771560 (Open Web Text)

Max Activating Token Index: 42

Text #12

Max Range: 4.9290. Min Range: -4.9290

Max Act: 4.6474. Min Act: -0.1700

Data Index: 7925807 (Open Web Text)

Max Activating Token Index: 412

Text #13

Max Range: 4.9290. Min Range: -4.9290

Max Act: 4.6378. Min Act: -0.1700

Data Index: 4374118 (Open Web Text)

Max Activating Token Index: 1008

Text #14

Max Range: 4.9290. Min Range: -4.9290

Max Act: 4.6292. Min Act: -0.1700

Data Index: 3015554 (Open Web Text)

Max Activating Token Index: 52

Text #15

Max Range: 4.9290. Min Range: -4.9290

Max Act: 4.6167. Min Act: -0.1700

Data Index: 7066928 (Open Web Text)

Max Activating Token Index: 492

Text #16

Max Range: 4.9290. Min Range: -4.9290

Max Act: 4.6376. Min Act: -0.1700

Data Index: 5925748 (Open Web Text)

Max Activating Token Index: 66

Text #17

Max Range: 4.9290. Min Range: -4.9290

Max Act: 4.6182. Min Act: -0.1700

Data Index: 6101527 (Open Web Text)

Max Activating Token Index: 500

Text #18

Max Range: 4.9290. Min Range: -4.9290

Max Act: 4.5776. Min Act: -0.1700

Data Index: 6295701 (Open Web Text)

Max Activating Token Index: 380

Text #19

Max Range: 4.9290. Min Range: -4.9290

Max Act: 4.6013. Min Act: -0.1700

Data Index: 1819628 (Open Web Text)

Max Activating Token Index: 51