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

Dataset: Open Web Text

Neuron 2156 in Layer 1

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: 3.7854. Min Range: -3.7854

Max Act: 3.7854. Min Act: -0.1700

Data Index: 2517899 (Open Web Text)

Max Activating Token Index: 117

Text #1

Max Range: 3.7854. Min Range: -3.7854

Max Act: 3.7514. Min Act: -0.1700

Data Index: 3881269 (Open Web Text)

Max Activating Token Index: 445

Text #2

Max Range: 3.7854. Min Range: -3.7854

Max Act: 3.7672. Min Act: -0.1700

Data Index: 2124868 (Open Web Text)

Max Activating Token Index: 281

Text #3

Max Range: 3.7854. Min Range: -3.7854

Max Act: 3.7207. Min Act: -0.1700

Data Index: 3952807 (Open Web Text)

Max Activating Token Index: 268

Text #4

Max Range: 3.7854. Min Range: -3.7854

Max Act: 3.7161. Min Act: -0.1700

Data Index: 8042768 (Open Web Text)

Max Activating Token Index: 349

Text #5

Max Range: 3.7854. Min Range: -3.7854

Max Act: 3.6767. Min Act: -0.1700

Data Index: 6139001 (Open Web Text)

Max Activating Token Index: 219

Text #6

Max Range: 3.7854. Min Range: -3.7854

Max Act: 3.6635. Min Act: -0.1700

Data Index: 2558603 (Open Web Text)

Max Activating Token Index: 525

Text #7

Max Range: 3.7854. Min Range: -3.7854

Max Act: 3.6597. Min Act: -0.1700

Data Index: 3066110 (Open Web Text)

Max Activating Token Index: 331

Text #8

Max Range: 3.7854. Min Range: -3.7854

Max Act: 3.6364. Min Act: -0.1700

Data Index: 7188546 (Open Web Text)

Max Activating Token Index: 478

Text #9

Max Range: 3.7854. Min Range: -3.7854

Max Act: 3.6371. Min Act: -0.1700

Data Index: 442149 (Open Web Text)

Max Activating Token Index: 233

Text #10

Max Range: 3.7854. Min Range: -3.7854

Max Act: 3.6320. Min Act: -0.1700

Data Index: 7941783 (Open Web Text)

Max Activating Token Index: 281

Text #11

Max Range: 3.7854. Min Range: -3.7854

Max Act: 3.6139. Min Act: -0.1700

Data Index: 4222378 (Open Web Text)

Max Activating Token Index: 318

Text #12

Max Range: 3.7854. Min Range: -3.7854

Max Act: 3.6248. Min Act: -0.1700

Data Index: 1667411 (Open Web Text)

Max Activating Token Index: 478

Text #13

Max Range: 3.7854. Min Range: -3.7854

Max Act: 3.5901. Min Act: -0.1700

Data Index: 1379782 (Open Web Text)

Max Activating Token Index: 661

Text #14

Max Range: 3.7854. Min Range: -3.7854

Max Act: 3.5896. Min Act: -0.1700

Data Index: 5122662 (Open Web Text)

Max Activating Token Index: 796

Text #15

Max Range: 3.7854. Min Range: -3.7854

Max Act: 3.5715. Min Act: -0.1700

Data Index: 6163582 (Open Web Text)

Max Activating Token Index: 781

Text #16

Max Range: 3.7854. Min Range: -3.7854

Max Act: 3.5568. Min Act: -0.1700

Data Index: 4740050 (Open Web Text)

Max Activating Token Index: 41

Text #17

Max Range: 3.7854. Min Range: -3.7854

Max Act: 3.5605. Min Act: -0.1700

Data Index: 1892863 (Open Web Text)

Max Activating Token Index: 853

Text #18

Max Range: 3.7854. Min Range: -3.7854

Max Act: 3.5653. Min Act: -0.1700

Data Index: 1500686 (Open Web Text)

Max Activating Token Index: 687

Text #19

Max Range: 3.7854. Min Range: -3.7854

Max Act: 3.5434. Min Act: -0.1700

Data Index: 975564 (Open Web Text)

Max Activating Token Index: 181