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

Dataset: Open Web Text

Neuron 336 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: 4.2673. Min Range: -4.2673

Max Act: 4.2673. Min Act: -0.1700

Data Index: 3292607 (Open Web Text)

Max Activating Token Index: 29

Text #1

Max Range: 4.2673. Min Range: -4.2673

Max Act: 4.0713. Min Act: -0.1700

Data Index: 5276704 (Open Web Text)

Max Activating Token Index: 23

Text #2

Max Range: 4.2673. Min Range: -4.2673

Max Act: 4.0388. Min Act: -0.1700

Data Index: 6898091 (Open Web Text)

Max Activating Token Index: 43

Text #3

Max Range: 4.2673. Min Range: -4.2673

Max Act: 3.8017. Min Act: -0.1700

Data Index: 5847571 (Open Web Text)

Max Activating Token Index: 337

Text #4

Max Range: 4.2673. Min Range: -4.2673

Max Act: 3.8026. Min Act: -0.1700

Data Index: 3225122 (Open Web Text)

Max Activating Token Index: 15

Text #5

Max Range: 4.2673. Min Range: -4.2673

Max Act: 3.8058. Min Act: -0.1700

Data Index: 4665193 (Open Web Text)

Max Activating Token Index: 823

Text #6

Max Range: 4.2673. Min Range: -4.2673

Max Act: 3.7090. Min Act: -0.1700

Data Index: 2733563 (Open Web Text)

Max Activating Token Index: 317

Text #7

Max Range: 4.2673. Min Range: -4.2673

Max Act: 3.6905. Min Act: -0.1700

Data Index: 5892238 (Open Web Text)

Max Activating Token Index: 14

Text #8

Max Range: 4.2673. Min Range: -4.2673

Max Act: 3.6856. Min Act: -0.1700

Data Index: 5245960 (Open Web Text)

Max Activating Token Index: 76

Text #9

Max Range: 4.2673. Min Range: -4.2673

Max Act: 3.6338. Min Act: -0.1700

Data Index: 1725671 (Open Web Text)

Max Activating Token Index: 368

Text #10

Max Range: 4.2673. Min Range: -4.2673

Max Act: 3.6322. Min Act: -0.1700

Data Index: 2397114 (Open Web Text)

Max Activating Token Index: 10

Text #11

Max Range: 4.2673. Min Range: -4.2673

Max Act: 3.6550. Min Act: -0.1700

Data Index: 2681044 (Open Web Text)

Max Activating Token Index: 8

Text #12

Max Range: 4.2673. Min Range: -4.2673

Max Act: 3.6488. Min Act: -0.1700

Data Index: 709768 (Open Web Text)

Max Activating Token Index: 763

Text #13

Max Range: 4.2673. Min Range: -4.2673

Max Act: 3.6136. Min Act: -0.1700

Data Index: 3255989 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 4.2673. Min Range: -4.2673

Max Act: 3.5915. Min Act: -0.1700

Data Index: 7721301 (Open Web Text)

Max Activating Token Index: 893

Text #15

Max Range: 4.2673. Min Range: -4.2673

Max Act: 3.6048. Min Act: -0.1700

Data Index: 1174610 (Open Web Text)

Max Activating Token Index: 817

Text #16

Max Range: 4.2673. Min Range: -4.2673

Max Act: 3.5591. Min Act: -0.1700

Data Index: 1607068 (Open Web Text)

Max Activating Token Index: 15

Text #17

Max Range: 4.2673. Min Range: -4.2673

Max Act: 3.5217. Min Act: -0.1700

Data Index: 2521077 (Open Web Text)

Max Activating Token Index: 159

Text #18

Max Range: 4.2673. Min Range: -4.2673

Max Act: 3.5350. Min Act: -0.1700

Data Index: 6333786 (Open Web Text)

Max Activating Token Index: 8

Text #19

Max Range: 4.2673. Min Range: -4.2673

Max Act: 3.5316. Min Act: -0.1700

Data Index: 837114 (Open Web Text)

Max Activating Token Index: 47