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

Dataset: Open Web Text

Neuron 2187 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: 6.3234. Min Range: -6.3234

Max Act: 6.3234. Min Act: -0.1700

Data Index: 4840901 (Open Web Text)

Max Activating Token Index: 843

Text #1

Max Range: 6.3234. Min Range: -6.3234

Max Act: 6.2921. Min Act: -0.1700

Data Index: 5508765 (Open Web Text)

Max Activating Token Index: 558

Text #2

Max Range: 6.3234. Min Range: -6.3234

Max Act: 6.3040. Min Act: -0.1700

Data Index: 2706525 (Open Web Text)

Max Activating Token Index: 477

Text #3

Max Range: 6.3234. Min Range: -6.3234

Max Act: 6.2790. Min Act: -0.1700

Data Index: 2571903 (Open Web Text)

Max Activating Token Index: 581

Text #4

Max Range: 6.3234. Min Range: -6.3234

Max Act: 6.2477. Min Act: -0.1700

Data Index: 8417137 (Open Web Text)

Max Activating Token Index: 585

Text #5

Max Range: 6.3234. Min Range: -6.3234

Max Act: 6.2651. Min Act: -0.1700

Data Index: 3678451 (Open Web Text)

Max Activating Token Index: 639

Text #6

Max Range: 6.3234. Min Range: -6.3234

Max Act: 6.2818. Min Act: -0.1700

Data Index: 8469873 (Open Web Text)

Max Activating Token Index: 1008

Text #7

Max Range: 6.3234. Min Range: -6.3234

Max Act: 6.2306. Min Act: -0.1700

Data Index: 8129428 (Open Web Text)

Max Activating Token Index: 575

Text #8

Max Range: 6.3234. Min Range: -6.3234

Max Act: 6.1903. Min Act: -0.1700

Data Index: 156808 (Open Web Text)

Max Activating Token Index: 548

Text #9

Max Range: 6.3234. Min Range: -6.3234

Max Act: 6.1842. Min Act: -0.1700

Data Index: 4371396 (Open Web Text)

Max Activating Token Index: 256

Text #10

Max Range: 6.3234. Min Range: -6.3234

Max Act: 6.1978. Min Act: -0.1700

Data Index: 8707860 (Open Web Text)

Max Activating Token Index: 605

Text #11

Max Range: 6.3234. Min Range: -6.3234

Max Act: 6.1696. Min Act: -0.1700

Data Index: 5793983 (Open Web Text)

Max Activating Token Index: 769

Text #12

Max Range: 6.3234. Min Range: -6.3234

Max Act: 6.1677. Min Act: -0.1700

Data Index: 4146975 (Open Web Text)

Max Activating Token Index: 782

Text #13

Max Range: 6.3234. Min Range: -6.3234

Max Act: 6.1616. Min Act: -0.1700

Data Index: 7335569 (Open Web Text)

Max Activating Token Index: 394

Text #14

Max Range: 6.3234. Min Range: -6.3234

Max Act: 6.1480. Min Act: -0.1700

Data Index: 2540424 (Open Web Text)

Max Activating Token Index: 1010

Text #15

Max Range: 6.3234. Min Range: -6.3234

Max Act: 6.1402. Min Act: -0.1700

Data Index: 1555347 (Open Web Text)

Max Activating Token Index: 666

Text #16

Max Range: 6.3234. Min Range: -6.3234

Max Act: 6.1322. Min Act: -0.1700

Data Index: 2614375 (Open Web Text)

Max Activating Token Index: 859

Text #17

Max Range: 6.3234. Min Range: -6.3234

Max Act: 6.1080. Min Act: -0.1700

Data Index: 5938489 (Open Web Text)

Max Activating Token Index: 981

Text #18

Max Range: 6.3234. Min Range: -6.3234

Max Act: 6.1182. Min Act: -0.1700

Data Index: 6148279 (Open Web Text)

Max Activating Token Index: 785

Text #19

Max Range: 6.3234. Min Range: -6.3234

Max Act: 6.1060. Min Act: -0.1700

Data Index: 6747447 (Open Web Text)

Max Activating Token Index: 845