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

Dataset: Open Web Text

Neuron 2600 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: 1.6255. Min Range: -1.6255

Max Act: 1.6255. Min Act: -0.1700

Data Index: 3184782 (Open Web Text)

Max Activating Token Index: 7

Text #1

Max Range: 1.6255. Min Range: -1.6255

Max Act: 1.5870. Min Act: -0.1700

Data Index: 2764562 (Open Web Text)

Max Activating Token Index: 49

Text #2

Max Range: 1.6255. Min Range: -1.6255

Max Act: 1.5710. Min Act: -0.1700

Data Index: 8099624 (Open Web Text)

Max Activating Token Index: 968

Text #3

Max Range: 1.6255. Min Range: -1.6255

Max Act: 1.5809. Min Act: -0.1700

Data Index: 1691848 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 1.6255. Min Range: -1.6255

Max Act: 1.5796. Min Act: -0.1700

Data Index: 4103371 (Open Web Text)

Max Activating Token Index: 540

Text #5

Max Range: 1.6255. Min Range: -1.6255

Max Act: 1.5727. Min Act: -0.1700

Data Index: 4955318 (Open Web Text)

Max Activating Token Index: 68

Text #6

Max Range: 1.6255. Min Range: -1.6255

Max Act: 1.5607. Min Act: -0.1700

Data Index: 3922068 (Open Web Text)

Max Activating Token Index: 85

Text #7

Max Range: 1.6255. Min Range: -1.6255

Max Act: 1.5473. Min Act: -0.1700

Data Index: 101418 (Open Web Text)

Max Activating Token Index: 649

Text #8

Max Range: 1.6255. Min Range: -1.6255

Max Act: 1.5353. Min Act: -0.1700

Data Index: 5899849 (Open Web Text)

Max Activating Token Index: 963

Text #9

Max Range: 1.6255. Min Range: -1.6255

Max Act: 1.5539. Min Act: -0.1700

Data Index: 2715082 (Open Web Text)

Max Activating Token Index: 795

Text #10

Max Range: 1.6255. Min Range: -1.6255

Max Act: 1.5438. Min Act: -0.1700

Data Index: 7109311 (Open Web Text)

Max Activating Token Index: 356

Text #11

Max Range: 1.6255. Min Range: -1.6255

Max Act: 1.5239. Min Act: -0.1700

Data Index: 7103347 (Open Web Text)

Max Activating Token Index: 793

Text #12

Max Range: 1.6255. Min Range: -1.6255

Max Act: 1.5360. Min Act: -0.1700

Data Index: 4365491 (Open Web Text)

Max Activating Token Index: 31

Text #13

Max Range: 1.6255. Min Range: -1.6255

Max Act: 1.5422. Min Act: -0.1700

Data Index: 5839790 (Open Web Text)

Max Activating Token Index: 629

Text #14

Max Range: 1.6255. Min Range: -1.6255

Max Act: 1.5180. Min Act: -0.1700

Data Index: 1215645 (Open Web Text)

Max Activating Token Index: 597

Text #15

Max Range: 1.6255. Min Range: -1.6255

Max Act: 1.5264. Min Act: -0.1698

Data Index: 1816671 (Open Web Text)

Max Activating Token Index: 172

Text #16

Max Range: 1.6255. Min Range: -1.6255

Max Act: 1.5295. Min Act: -0.1700

Data Index: 935505 (Open Web Text)

Max Activating Token Index: 654

Text #17

Max Range: 1.6255. Min Range: -1.6255

Max Act: 1.5211. Min Act: -0.1700

Data Index: 4110383 (Open Web Text)

Max Activating Token Index: 1009

Text #18

Max Range: 1.6255. Min Range: -1.6255

Max Act: 1.5259. Min Act: -0.1700

Data Index: 476981 (Open Web Text)

Max Activating Token Index: 449

Text #19

Max Range: 1.6255. Min Range: -1.6255

Max Act: 1.5254. Min Act: -0.1699

Data Index: 2794898 (Open Web Text)

Max Activating Token Index: 114