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

Dataset: Open Web Text

Neuron 250 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: 3.8743. Min Range: -3.8743

Max Act: 3.8664. Min Act: -0.1700

Data Index: 3278920 (Open Web Text)

Max Activating Token Index: 39

Text #1

Max Range: 3.8743. Min Range: -3.8743

Max Act: 3.8743. Min Act: -0.1700

Data Index: 1761996 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 3.8743. Min Range: -3.8743

Max Act: 3.8148. Min Act: -0.1700

Data Index: 1661592 (Open Web Text)

Max Activating Token Index: 20

Text #3

Max Range: 3.8743. Min Range: -3.8743

Max Act: 3.8335. Min Act: -0.1700

Data Index: 1979570 (Open Web Text)

Max Activating Token Index: 52

Text #4

Max Range: 3.8743. Min Range: -3.8743

Max Act: 3.7868. Min Act: -0.1700

Data Index: 6496985 (Open Web Text)

Max Activating Token Index: 13

Text #5

Max Range: 3.8743. Min Range: -3.8743

Max Act: 3.7867. Min Act: -0.1700

Data Index: 2019006 (Open Web Text)

Max Activating Token Index: 450

Text #6

Max Range: 3.8743. Min Range: -3.8743

Max Act: 3.7657. Min Act: -0.1700

Data Index: 4385968 (Open Web Text)

Max Activating Token Index: 20

Text #7

Max Range: 3.8743. Min Range: -3.8743

Max Act: 3.7616. Min Act: -0.1700

Data Index: 5716013 (Open Web Text)

Max Activating Token Index: 43

Text #8

Max Range: 3.8743. Min Range: -3.8743

Max Act: 3.7539. Min Act: -0.1700

Data Index: 6183737 (Open Web Text)

Max Activating Token Index: 34

Text #9

Max Range: 3.8743. Min Range: -3.8743

Max Act: 3.7398. Min Act: -0.1700

Data Index: 221362 (Open Web Text)

Max Activating Token Index: 8

Text #10

Max Range: 3.8743. Min Range: -3.8743

Max Act: 3.7510. Min Act: -0.1700

Data Index: 3825777 (Open Web Text)

Max Activating Token Index: 17

Text #11

Max Range: 3.8743. Min Range: -3.8743

Max Act: 3.7279. Min Act: -0.1700

Data Index: 3348476 (Open Web Text)

Max Activating Token Index: 16

Text #12

Max Range: 3.8743. Min Range: -3.8743

Max Act: 3.7453. Min Act: -0.1700

Data Index: 7272159 (Open Web Text)

Max Activating Token Index: 108

Text #13

Max Range: 3.8743. Min Range: -3.8743

Max Act: 3.7424. Min Act: -0.1700

Data Index: 6476234 (Open Web Text)

Max Activating Token Index: 110

Text #14

Max Range: 3.8743. Min Range: -3.8743

Max Act: 3.7455. Min Act: -0.1700

Data Index: 3179162 (Open Web Text)

Max Activating Token Index: 47

Text #15

Max Range: 3.8743. Min Range: -3.8743

Max Act: 3.7446. Min Act: -0.1700

Data Index: 5076817 (Open Web Text)

Max Activating Token Index: 40

Text #16

Max Range: 3.8743. Min Range: -3.8743

Max Act: 3.7525. Min Act: -0.1700

Data Index: 1056280 (Open Web Text)

Max Activating Token Index: 7

Text #17

Max Range: 3.8743. Min Range: -3.8743

Max Act: 3.7100. Min Act: -0.1700

Data Index: 24557 (Open Web Text)

Max Activating Token Index: 22

Text #18

Max Range: 3.8743. Min Range: -3.8743

Max Act: 3.7024. Min Act: -0.1700

Data Index: 3825781 (Open Web Text)

Max Activating Token Index: 62

Text #19

Max Range: 3.8743. Min Range: -3.8743

Max Act: 3.7173. Min Act: -0.1700

Data Index: 140861 (Open Web Text)

Max Activating Token Index: 111