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

Dataset: Open Web Text

Neuron 1682 in Layer 6

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: 6.0108. Min Range: -6.0108

Max Act: 6.0108. Min Act: -0.1700

Data Index: 8772689 (Open Web Text)

Max Activating Token Index: 765

Text #1

Max Range: 6.0108. Min Range: -6.0108

Max Act: 5.9314. Min Act: -0.1700

Data Index: 3591506 (Open Web Text)

Max Activating Token Index: 502

Text #2

Max Range: 6.0108. Min Range: -6.0108

Max Act: 5.8581. Min Act: -0.1700

Data Index: 209851 (Open Web Text)

Max Activating Token Index: 517

Text #3

Max Range: 6.0108. Min Range: -6.0108

Max Act: 5.8323. Min Act: -0.1700

Data Index: 8066834 (Open Web Text)

Max Activating Token Index: 980

Text #4

Max Range: 6.0108. Min Range: -6.0108

Max Act: 5.8304. Min Act: -0.1700

Data Index: 4557755 (Open Web Text)

Max Activating Token Index: 300

Text #5

Max Range: 6.0108. Min Range: -6.0108

Max Act: 5.8574. Min Act: -0.1700

Data Index: 2193137 (Open Web Text)

Max Activating Token Index: 785

Text #6

Max Range: 6.0108. Min Range: -6.0108

Max Act: 5.7889. Min Act: -0.1700

Data Index: 4516730 (Open Web Text)

Max Activating Token Index: 831

Text #7

Max Range: 6.0108. Min Range: -6.0108

Max Act: 5.7792. Min Act: -0.1700

Data Index: 2028945 (Open Web Text)

Max Activating Token Index: 393

Text #8

Max Range: 6.0108. Min Range: -6.0108

Max Act: 5.7683. Min Act: -0.1700

Data Index: 6325645 (Open Web Text)

Max Activating Token Index: 540

Text #9

Max Range: 6.0108. Min Range: -6.0108

Max Act: 5.7851. Min Act: -0.1700

Data Index: 8695478 (Open Web Text)

Max Activating Token Index: 762

Text #10

Max Range: 6.0108. Min Range: -6.0108

Max Act: 5.7216. Min Act: -0.1700

Data Index: 4139923 (Open Web Text)

Max Activating Token Index: 929

Text #11

Max Range: 6.0108. Min Range: -6.0108

Max Act: 5.6644. Min Act: -0.1700

Data Index: 1098857 (Open Web Text)

Max Activating Token Index: 850

Text #12

Max Range: 6.0108. Min Range: -6.0108

Max Act: 5.6544. Min Act: -0.1700

Data Index: 1457741 (Open Web Text)

Max Activating Token Index: 469

Text #13

Max Range: 6.0108. Min Range: -6.0108

Max Act: 5.6937. Min Act: -0.1700

Data Index: 6645141 (Open Web Text)

Max Activating Token Index: 980

Text #14

Max Range: 6.0108. Min Range: -6.0108

Max Act: 5.6688. Min Act: -0.1700

Data Index: 3733958 (Open Web Text)

Max Activating Token Index: 294

Text #15

Max Range: 6.0108. Min Range: -6.0108

Max Act: 5.5949. Min Act: -0.1700

Data Index: 2820524 (Open Web Text)

Max Activating Token Index: 329

Text #16

Max Range: 6.0108. Min Range: -6.0108

Max Act: 5.6209. Min Act: -0.1700

Data Index: 2287699 (Open Web Text)

Max Activating Token Index: 921

Text #17

Max Range: 6.0108. Min Range: -6.0108

Max Act: 5.5982. Min Act: -0.1700

Data Index: 1703871 (Open Web Text)

Max Activating Token Index: 375

Text #18

Max Range: 6.0108. Min Range: -6.0108

Max Act: 5.5991. Min Act: -0.1700

Data Index: 6700435 (Open Web Text)

Max Activating Token Index: 718

Text #19

Max Range: 6.0108. Min Range: -6.0108

Max Act: 5.5934. Min Act: -0.1700

Data Index: 7671197 (Open Web Text)

Max Activating Token Index: 986