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

Dataset: Open Web Text

Neuron 1799 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: 4.6906. Min Range: -4.6906

Max Act: 4.6906. Min Act: -0.1700

Data Index: 3463401 (Open Web Text)

Max Activating Token Index: 815

Text #1

Max Range: 4.6906. Min Range: -4.6906

Max Act: 4.6001. Min Act: -0.1700

Data Index: 2379927 (Open Web Text)

Max Activating Token Index: 140

Text #2

Max Range: 4.6906. Min Range: -4.6906

Max Act: 4.5771. Min Act: -0.1700

Data Index: 1383919 (Open Web Text)

Max Activating Token Index: 314

Text #3

Max Range: 4.6906. Min Range: -4.6906

Max Act: 4.4796. Min Act: -0.1700

Data Index: 2203075 (Open Web Text)

Max Activating Token Index: 496

Text #4

Max Range: 4.6906. Min Range: -4.6906

Max Act: 4.4396. Min Act: -0.1700

Data Index: 6680804 (Open Web Text)

Max Activating Token Index: 556

Text #5

Max Range: 4.6906. Min Range: -4.6906

Max Act: 4.4644. Min Act: -0.1700

Data Index: 7222744 (Open Web Text)

Max Activating Token Index: 484

Text #6

Max Range: 4.6906. Min Range: -4.6906

Max Act: 4.3767. Min Act: -0.1700

Data Index: 1155846 (Open Web Text)

Max Activating Token Index: 523

Text #7

Max Range: 4.6906. Min Range: -4.6906

Max Act: 4.3423. Min Act: -0.1700

Data Index: 4684627 (Open Web Text)

Max Activating Token Index: 540

Text #8

Max Range: 4.6906. Min Range: -4.6906

Max Act: 4.3516. Min Act: -0.1700

Data Index: 5739820 (Open Web Text)

Max Activating Token Index: 688

Text #9

Max Range: 4.6906. Min Range: -4.6906

Max Act: 4.3376. Min Act: -0.1700

Data Index: 3146272 (Open Web Text)

Max Activating Token Index: 908

Text #10

Max Range: 4.6906. Min Range: -4.6906

Max Act: 4.2799. Min Act: -0.1700

Data Index: 1565809 (Open Web Text)

Max Activating Token Index: 200

Text #11

Max Range: 4.6906. Min Range: -4.6906

Max Act: 4.2703. Min Act: -0.1700

Data Index: 6272508 (Open Web Text)

Max Activating Token Index: 968

Text #12

Max Range: 4.6906. Min Range: -4.6906

Max Act: 4.2966. Min Act: -0.1700

Data Index: 7370324 (Open Web Text)

Max Activating Token Index: 773

Text #13

Max Range: 4.6906. Min Range: -4.6906

Max Act: 4.2573. Min Act: -0.1700

Data Index: 1824547 (Open Web Text)

Max Activating Token Index: 68

Text #14

Max Range: 4.6906. Min Range: -4.6906

Max Act: 4.2375. Min Act: -0.1700

Data Index: 1904231 (Open Web Text)

Max Activating Token Index: 408

Text #15

Max Range: 4.6906. Min Range: -4.6906

Max Act: 4.2306. Min Act: -0.1700

Data Index: 564767 (Open Web Text)

Max Activating Token Index: 775

Text #16

Max Range: 4.6906. Min Range: -4.6906

Max Act: 4.2321. Min Act: -0.1700

Data Index: 946338 (Open Web Text)

Max Activating Token Index: 1013

Text #17

Max Range: 4.6906. Min Range: -4.6906

Max Act: 4.2579. Min Act: -0.1700

Data Index: 5578055 (Open Web Text)

Max Activating Token Index: 129

Text #18

Max Range: 4.6906. Min Range: -4.6906

Max Act: 4.2731. Min Act: -0.1700

Data Index: 6763197 (Open Web Text)

Max Activating Token Index: 380

Text #19

Max Range: 4.6906. Min Range: -4.6906

Max Act: 4.2396. Min Act: -0.1700

Data Index: 2873485 (Open Web Text)

Max Activating Token Index: 588