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

Dataset: Open Web Text

Neuron 2236 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: 2.1044. Min Range: -2.1044

Max Act: 2.1044. Min Act: -0.1700

Data Index: 5001260 (Open Web Text)

Max Activating Token Index: 9

Text #1

Max Range: 2.1044. Min Range: -2.1044

Max Act: 2.0810. Min Act: -0.1700

Data Index: 522974 (Open Web Text)

Max Activating Token Index: 2

Text #2

Max Range: 2.1044. Min Range: -2.1044

Max Act: 2.0601. Min Act: -0.1700

Data Index: 500665 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 2.1044. Min Range: -2.1044

Max Act: 2.0708. Min Act: -0.1700

Data Index: 4288346 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 2.1044. Min Range: -2.1044

Max Act: 2.0660. Min Act: -0.1700

Data Index: 5814896 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 2.1044. Min Range: -2.1044

Max Act: 2.0627. Min Act: -0.1700

Data Index: 634167 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 2.1044. Min Range: -2.1044

Max Act: 2.0610. Min Act: -0.1691

Data Index: 4462680 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 2.1044. Min Range: -2.1044

Max Act: 2.0452. Min Act: -0.1700

Data Index: 2056678 (Open Web Text)

Max Activating Token Index: 7

Text #8

Max Range: 2.1044. Min Range: -2.1044

Max Act: 2.0549. Min Act: -0.1700

Data Index: 6692334 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 2.1044. Min Range: -2.1044

Max Act: 2.0467. Min Act: -0.1700

Data Index: 4364114 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 2.1044. Min Range: -2.1044

Max Act: 2.0376. Min Act: -0.1700

Data Index: 5763209 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 2.1044. Min Range: -2.1044

Max Act: 2.0393. Min Act: -0.1700

Data Index: 4915320 (Open Web Text)

Max Activating Token Index: 10

Text #12

Max Range: 2.1044. Min Range: -2.1044

Max Act: 2.0401. Min Act: -0.1700

Data Index: 2885512 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 2.1044. Min Range: -2.1044

Max Act: 2.0397. Min Act: -0.1700

Data Index: 5406267 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 2.1044. Min Range: -2.1044

Max Act: 2.0342. Min Act: -0.1699

Data Index: 8766958 (Open Web Text)

Max Activating Token Index: 652

Text #15

Max Range: 2.1044. Min Range: -2.1044

Max Act: 2.0332. Min Act: -0.1700

Data Index: 4871037 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 2.1044. Min Range: -2.1044

Max Act: 2.0339. Min Act: -0.1697

Data Index: 7955694 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 2.1044. Min Range: -2.1044

Max Act: 2.0264. Min Act: -0.1700

Data Index: 1945702 (Open Web Text)

Max Activating Token Index: 7

Text #18

Max Range: 2.1044. Min Range: -2.1044

Max Act: 2.0249. Min Act: -0.1700

Data Index: 950182 (Open Web Text)

Max Activating Token Index: 8

Text #19

Max Range: 2.1044. Min Range: -2.1044

Max Act: 2.0303. Min Act: -0.1700

Data Index: 2547701 (Open Web Text)

Max Activating Token Index: 762