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

Dataset: Open Web Text

Neuron 1922 in Layer 2

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: 3.0410. Min Range: -3.0410

Max Act: 3.0410. Min Act: -0.1700

Data Index: 3894570 (Open Web Text)

Max Activating Token Index: 226

Text #1

Max Range: 3.0410. Min Range: -3.0410

Max Act: 3.0364. Min Act: -0.1700

Data Index: 2082315 (Open Web Text)

Max Activating Token Index: 978

Text #2

Max Range: 3.0410. Min Range: -3.0410

Max Act: 3.0078. Min Act: -0.1700

Data Index: 6094067 (Open Web Text)

Max Activating Token Index: 576

Text #3

Max Range: 3.0410. Min Range: -3.0410

Max Act: 2.9930. Min Act: -0.1700

Data Index: 1105972 (Open Web Text)

Max Activating Token Index: 336

Text #4

Max Range: 3.0410. Min Range: -3.0410

Max Act: 2.9584. Min Act: -0.1700

Data Index: 6269206 (Open Web Text)

Max Activating Token Index: 109

Text #5

Max Range: 3.0410. Min Range: -3.0410

Max Act: 2.9463. Min Act: -0.1700

Data Index: 1015059 (Open Web Text)

Max Activating Token Index: 673

Text #6

Max Range: 3.0410. Min Range: -3.0410

Max Act: 2.9524. Min Act: -0.1700

Data Index: 5976816 (Open Web Text)

Max Activating Token Index: 85

Text #7

Max Range: 3.0410. Min Range: -3.0410

Max Act: 2.9454. Min Act: -0.1700

Data Index: 2296884 (Open Web Text)

Max Activating Token Index: 457

Text #8

Max Range: 3.0410. Min Range: -3.0410

Max Act: 2.9253. Min Act: -0.1700

Data Index: 3084811 (Open Web Text)

Max Activating Token Index: 93

Text #9

Max Range: 3.0410. Min Range: -3.0410

Max Act: 2.9068. Min Act: -0.1700

Data Index: 6453765 (Open Web Text)

Max Activating Token Index: 622

Text #10

Max Range: 3.0410. Min Range: -3.0410

Max Act: 2.9247. Min Act: -0.1700

Data Index: 2559407 (Open Web Text)

Max Activating Token Index: 569

Text #11

Max Range: 3.0410. Min Range: -3.0410

Max Act: 2.9057. Min Act: -0.1700

Data Index: 992308 (Open Web Text)

Max Activating Token Index: 709

Text #12

Max Range: 3.0410. Min Range: -3.0410

Max Act: 2.9067. Min Act: -0.1700

Data Index: 7607525 (Open Web Text)

Max Activating Token Index: 599

Text #13

Max Range: 3.0410. Min Range: -3.0410

Max Act: 2.9335. Min Act: -0.1700

Data Index: 4502566 (Open Web Text)

Max Activating Token Index: 429

Text #14

Max Range: 3.0410. Min Range: -3.0410

Max Act: 2.8979. Min Act: -0.1700

Data Index: 2646976 (Open Web Text)

Max Activating Token Index: 744

Text #15

Max Range: 3.0410. Min Range: -3.0410

Max Act: 2.8952. Min Act: -0.1700

Data Index: 4618711 (Open Web Text)

Max Activating Token Index: 208

Text #16

Max Range: 3.0410. Min Range: -3.0410

Max Act: 2.8895. Min Act: -0.1700

Data Index: 1976946 (Open Web Text)

Max Activating Token Index: 199

Text #17

Max Range: 3.0410. Min Range: -3.0410

Max Act: 2.8927. Min Act: -0.1700

Data Index: 759997 (Open Web Text)

Max Activating Token Index: 289

Text #18

Max Range: 3.0410. Min Range: -3.0410

Max Act: 2.8705. Min Act: -0.1700

Data Index: 5117953 (Open Web Text)

Max Activating Token Index: 490

Text #19

Max Range: 3.0410. Min Range: -3.0410

Max Act: 2.8925. Min Act: -0.1700

Data Index: 5535807 (Open Web Text)

Max Activating Token Index: 477