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

Dataset: Open Web Text

Neuron 2769 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: 3.9487. Min Range: -3.9487

Max Act: 3.9338. Min Act: -0.1700

Data Index: 2442281 (Open Web Text)

Max Activating Token Index: 14

Text #1

Max Range: 3.9487. Min Range: -3.9487

Max Act: 3.9487. Min Act: -0.1700

Data Index: 6587485 (Open Web Text)

Max Activating Token Index: 956

Text #2

Max Range: 3.9487. Min Range: -3.9487

Max Act: 3.8167. Min Act: -0.1700

Data Index: 683342 (Open Web Text)

Max Activating Token Index: 940

Text #3

Max Range: 3.9487. Min Range: -3.9487

Max Act: 3.7951. Min Act: -0.1700

Data Index: 3091623 (Open Web Text)

Max Activating Token Index: 1023

Text #4

Max Range: 3.9487. Min Range: -3.9487

Max Act: 3.8187. Min Act: -0.1700

Data Index: 4062997 (Open Web Text)

Max Activating Token Index: 142

Text #5

Max Range: 3.9487. Min Range: -3.9487

Max Act: 3.7658. Min Act: -0.1700

Data Index: 8555327 (Open Web Text)

Max Activating Token Index: 494

Text #6

Max Range: 3.9487. Min Range: -3.9487

Max Act: 3.7506. Min Act: -0.1700

Data Index: 5034134 (Open Web Text)

Max Activating Token Index: 847

Text #7

Max Range: 3.9487. Min Range: -3.9487

Max Act: 3.7927. Min Act: -0.1700

Data Index: 7942873 (Open Web Text)

Max Activating Token Index: 387

Text #8

Max Range: 3.9487. Min Range: -3.9487

Max Act: 3.7620. Min Act: -0.1700

Data Index: 420791 (Open Web Text)

Max Activating Token Index: 280

Text #9

Max Range: 3.9487. Min Range: -3.9487

Max Act: 3.7473. Min Act: -0.1700

Data Index: 5656428 (Open Web Text)

Max Activating Token Index: 14

Text #10

Max Range: 3.9487. Min Range: -3.9487

Max Act: 3.7650. Min Act: -0.1700

Data Index: 1484820 (Open Web Text)

Max Activating Token Index: 369

Text #11

Max Range: 3.9487. Min Range: -3.9487

Max Act: 3.7461. Min Act: -0.1700

Data Index: 5694014 (Open Web Text)

Max Activating Token Index: 62

Text #12

Max Range: 3.9487. Min Range: -3.9487

Max Act: 3.7437. Min Act: -0.1700

Data Index: 6758131 (Open Web Text)

Max Activating Token Index: 925

Text #13

Max Range: 3.9487. Min Range: -3.9487

Max Act: 3.7323. Min Act: -0.1700

Data Index: 2096672 (Open Web Text)

Max Activating Token Index: 514

Text #14

Max Range: 3.9487. Min Range: -3.9487

Max Act: 3.6991. Min Act: -0.1700

Data Index: 6776631 (Open Web Text)

Max Activating Token Index: 659

Text #15

Max Range: 3.9487. Min Range: -3.9487

Max Act: 3.7183. Min Act: -0.1700

Data Index: 2159438 (Open Web Text)

Max Activating Token Index: 849

Text #16

Max Range: 3.9487. Min Range: -3.9487

Max Act: 3.7234. Min Act: -0.1700

Data Index: 3987555 (Open Web Text)

Max Activating Token Index: 1012

Text #17

Max Range: 3.9487. Min Range: -3.9487

Max Act: 3.7076. Min Act: -0.1700

Data Index: 1070809 (Open Web Text)

Max Activating Token Index: 65

Text #18

Max Range: 3.9487. Min Range: -3.9487

Max Act: 3.7116. Min Act: -0.1700

Data Index: 6902322 (Open Web Text)

Max Activating Token Index: 214

Text #19

Max Range: 3.9487. Min Range: -3.9487

Max Act: 3.7278. Min Act: -0.1700

Data Index: 1341969 (Open Web Text)

Max Activating Token Index: 329