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

Dataset: Open Web Text

Neuron 1419 in Layer 0

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: 3.1006. Min Range: -3.1006

Max Act: 3.1006. Min Act: -0.1700

Data Index: 1391441 (Open Web Text)

Max Activating Token Index: 975

Text #1

Max Range: 3.1006. Min Range: -3.1006

Max Act: 3.0061. Min Act: -0.1700

Data Index: 664077 (Open Web Text)

Max Activating Token Index: 1017

Text #2

Max Range: 3.1006. Min Range: -3.1006

Max Act: 2.9786. Min Act: -0.1700

Data Index: 8443217 (Open Web Text)

Max Activating Token Index: 931

Text #3

Max Range: 3.1006. Min Range: -3.1006

Max Act: 2.9591. Min Act: -0.1700

Data Index: 5229628 (Open Web Text)

Max Activating Token Index: 138

Text #4

Max Range: 3.1006. Min Range: -3.1006

Max Act: 2.9473. Min Act: -0.1700

Data Index: 2808959 (Open Web Text)

Max Activating Token Index: 785

Text #5

Max Range: 3.1006. Min Range: -3.1006

Max Act: 2.9479. Min Act: -0.1700

Data Index: 3657571 (Open Web Text)

Max Activating Token Index: 864

Text #6

Max Range: 3.1006. Min Range: -3.1006

Max Act: 2.9573. Min Act: -0.1700

Data Index: 2555848 (Open Web Text)

Max Activating Token Index: 643

Text #7

Max Range: 3.1006. Min Range: -3.1006

Max Act: 2.9459. Min Act: -0.1700

Data Index: 6199751 (Open Web Text)

Max Activating Token Index: 75

Text #8

Max Range: 3.1006. Min Range: -3.1006

Max Act: 2.9417. Min Act: -0.1700

Data Index: 8015958 (Open Web Text)

Max Activating Token Index: 45

Text #9

Max Range: 3.1006. Min Range: -3.1006

Max Act: 2.9390. Min Act: -0.1700

Data Index: 2498369 (Open Web Text)

Max Activating Token Index: 689

Text #10

Max Range: 3.1006. Min Range: -3.1006

Max Act: 2.9194. Min Act: -0.1700

Data Index: 4842066 (Open Web Text)

Max Activating Token Index: 35

Text #11

Max Range: 3.1006. Min Range: -3.1006

Max Act: 2.9267. Min Act: -0.1700

Data Index: 1010765 (Open Web Text)

Max Activating Token Index: 555

Text #12

Max Range: 3.1006. Min Range: -3.1006

Max Act: 2.9291. Min Act: -0.1700

Data Index: 5374710 (Open Web Text)

Max Activating Token Index: 757

Text #13

Max Range: 3.1006. Min Range: -3.1006

Max Act: 2.9321. Min Act: -0.1700

Data Index: 6489020 (Open Web Text)

Max Activating Token Index: 558

Text #14

Max Range: 3.1006. Min Range: -3.1006

Max Act: 2.9121. Min Act: -0.1700

Data Index: 7571867 (Open Web Text)

Max Activating Token Index: 463

Text #15

Max Range: 3.1006. Min Range: -3.1006

Max Act: 2.9112. Min Act: -0.1700

Data Index: 846253 (Open Web Text)

Max Activating Token Index: 530

Text #16

Max Range: 3.1006. Min Range: -3.1006

Max Act: 2.9070. Min Act: -0.1700

Data Index: 3660403 (Open Web Text)

Max Activating Token Index: 391

Text #17

Max Range: 3.1006. Min Range: -3.1006

Max Act: 2.9058. Min Act: -0.1700

Data Index: 3691737 (Open Web Text)

Max Activating Token Index: 932

Text #18

Max Range: 3.1006. Min Range: -3.1006

Max Act: 2.8926. Min Act: -0.1700

Data Index: 2735641 (Open Web Text)

Max Activating Token Index: 304

Text #19

Max Range: 3.1006. Min Range: -3.1006

Max Act: 2.8871. Min Act: -0.1700

Data Index: 6276002 (Open Web Text)

Max Activating Token Index: 711