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

Dataset: Open Web Text

Neuron 2475 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: 4.4919. Min Range: -4.4919

Max Act: 4.4826. Min Act: -0.1700

Data Index: 4428213 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 4.4919. Min Range: -4.4919

Max Act: 4.4919. Min Act: -0.1700

Data Index: 379646 (Open Web Text)

Max Activating Token Index: 12

Text #2

Max Range: 4.4919. Min Range: -4.4919

Max Act: 4.4353. Min Act: -0.1700

Data Index: 4442278 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 4.4919. Min Range: -4.4919

Max Act: 4.4086. Min Act: -0.1700

Data Index: 7862953 (Open Web Text)

Max Activating Token Index: 8

Text #4

Max Range: 4.4919. Min Range: -4.4919

Max Act: 4.4051. Min Act: -0.1700

Data Index: 8241605 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 4.4919. Min Range: -4.4919

Max Act: 4.3865. Min Act: -0.1700

Data Index: 2140319 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 4.4919. Min Range: -4.4919

Max Act: 4.4066. Min Act: -0.1700

Data Index: 390820 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 4.4919. Min Range: -4.4919

Max Act: 4.3988. Min Act: -0.1700

Data Index: 7950915 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 4.4919. Min Range: -4.4919

Max Act: 4.3755. Min Act: -0.1700

Data Index: 3238759 (Open Web Text)

Max Activating Token Index: 10

Text #9

Max Range: 4.4919. Min Range: -4.4919

Max Act: 4.3675. Min Act: -0.1700

Data Index: 1511835 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 4.4919. Min Range: -4.4919

Max Act: 4.3565. Min Act: -0.1700

Data Index: 7209061 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 4.4919. Min Range: -4.4919

Max Act: 4.3636. Min Act: -0.1700

Data Index: 984762 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 4.4919. Min Range: -4.4919

Max Act: 4.3475. Min Act: -0.1700

Data Index: 1487565 (Open Web Text)

Max Activating Token Index: 7

Text #13

Max Range: 4.4919. Min Range: -4.4919

Max Act: 4.3295. Min Act: -0.1700

Data Index: 6210642 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 4.4919. Min Range: -4.4919

Max Act: 4.3390. Min Act: -0.1700

Data Index: 1556356 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 4.4919. Min Range: -4.4919

Max Act: 4.3331. Min Act: -0.1700

Data Index: 1254581 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 4.4919. Min Range: -4.4919

Max Act: 4.3144. Min Act: -0.1700

Data Index: 1867814 (Open Web Text)

Max Activating Token Index: 11

Text #17

Max Range: 4.4919. Min Range: -4.4919

Max Act: 4.3205. Min Act: -0.1700

Data Index: 3408317 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 4.4919. Min Range: -4.4919

Max Act: 4.2974. Min Act: -0.1700

Data Index: 55687 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 4.4919. Min Range: -4.4919

Max Act: 4.3069. Min Act: -0.1700

Data Index: 4983382 (Open Web Text)

Max Activating Token Index: 6