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

Dataset: Open Web Text

Neuron 2865 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: 4.4988. Min Range: -4.4988

Max Act: 4.4988. Min Act: -0.1699

Data Index: 3381063 (Open Web Text)

Max Activating Token Index: 75

Text #1

Max Range: 4.4988. Min Range: -4.4988

Max Act: 4.4627. Min Act: -0.1700

Data Index: 5800758 (Open Web Text)

Max Activating Token Index: 2

Text #2

Max Range: 4.4988. Min Range: -4.4988

Max Act: 4.4065. Min Act: -0.1700

Data Index: 8127666 (Open Web Text)

Max Activating Token Index: 41

Text #3

Max Range: 4.4988. Min Range: -4.4988

Max Act: 4.3339. Min Act: -0.1700

Data Index: 4084022 (Open Web Text)

Max Activating Token Index: 266

Text #4

Max Range: 4.4988. Min Range: -4.4988

Max Act: 4.3161. Min Act: -0.1700

Data Index: 5000798 (Open Web Text)

Max Activating Token Index: 407

Text #5

Max Range: 4.4988. Min Range: -4.4988

Max Act: 4.3231. Min Act: -0.1693

Data Index: 4563970 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 4.4988. Min Range: -4.4988

Max Act: 4.2291. Min Act: -0.1700

Data Index: 2970029 (Open Web Text)

Max Activating Token Index: 692

Text #7

Max Range: 4.4988. Min Range: -4.4988

Max Act: 4.2771. Min Act: -0.1700

Data Index: 843544 (Open Web Text)

Max Activating Token Index: 157

Text #8

Max Range: 4.4988. Min Range: -4.4988

Max Act: 4.2525. Min Act: -0.1700

Data Index: 2242014 (Open Web Text)

Max Activating Token Index: 580

Text #9

Max Range: 4.4988. Min Range: -4.4988

Max Act: 4.2496. Min Act: -0.1700

Data Index: 1533926 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 4.4988. Min Range: -4.4988

Max Act: 4.2357. Min Act: -0.1700

Data Index: 1558805 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 4.4988. Min Range: -4.4988

Max Act: 4.2357. Min Act: -0.1700

Data Index: 43897 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 4.4988. Min Range: -4.4988

Max Act: 4.2131. Min Act: -0.1700

Data Index: 6469282 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 4.4988. Min Range: -4.4988

Max Act: 4.2191. Min Act: -0.1700

Data Index: 2674904 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 4.4988. Min Range: -4.4988

Max Act: 4.1689. Min Act: -0.1700

Data Index: 8278833 (Open Web Text)

Max Activating Token Index: 190

Text #15

Max Range: 4.4988. Min Range: -4.4988

Max Act: 4.1938. Min Act: -0.1700

Data Index: 7892007 (Open Web Text)

Max Activating Token Index: 106

Text #16

Max Range: 4.4988. Min Range: -4.4988

Max Act: 4.2044. Min Act: -0.1700

Data Index: 5018620 (Open Web Text)

Max Activating Token Index: 932

Text #17

Max Range: 4.4988. Min Range: -4.4988

Max Act: 4.2056. Min Act: -0.1700

Data Index: 2624498 (Open Web Text)

Max Activating Token Index: 11

Text #18

Max Range: 4.4988. Min Range: -4.4988

Max Act: 4.1886. Min Act: -0.1700

Data Index: 863072 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 4.4988. Min Range: -4.4988

Max Act: 4.1496. Min Act: -0.1700

Data Index: 2582998 (Open Web Text)

Max Activating Token Index: 2