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

Dataset: Open Web Text

Neuron 1870 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: 3.2915. Min Range: -3.2915

Max Act: 3.2915. Min Act: -0.1700

Data Index: 2480165 (Open Web Text)

Max Activating Token Index: 15

Text #1

Max Range: 3.2915. Min Range: -3.2915

Max Act: 3.2688. Min Act: -0.1700

Data Index: 6942792 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 3.2915. Min Range: -3.2915

Max Act: 3.2598. Min Act: -0.1700

Data Index: 6275674 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 3.2915. Min Range: -3.2915

Max Act: 3.2359. Min Act: -0.1700

Data Index: 7737790 (Open Web Text)

Max Activating Token Index: 11

Text #4

Max Range: 3.2915. Min Range: -3.2915

Max Act: 3.2178. Min Act: -0.1700

Data Index: 2023644 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 3.2915. Min Range: -3.2915

Max Act: 3.2038. Min Act: -0.1700

Data Index: 525912 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 3.2915. Min Range: -3.2915

Max Act: 3.1698. Min Act: -0.1700

Data Index: 3956563 (Open Web Text)

Max Activating Token Index: 7

Text #7

Max Range: 3.2915. Min Range: -3.2915

Max Act: 3.1819. Min Act: -0.1700

Data Index: 1095449 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 3.2915. Min Range: -3.2915

Max Act: 3.1706. Min Act: -0.1700

Data Index: 8222766 (Open Web Text)

Max Activating Token Index: 8

Text #9

Max Range: 3.2915. Min Range: -3.2915

Max Act: 3.1616. Min Act: -0.1700

Data Index: 4520485 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 3.2915. Min Range: -3.2915

Max Act: 3.1535. Min Act: -0.1700

Data Index: 4944558 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 3.2915. Min Range: -3.2915

Max Act: 3.1472. Min Act: -0.1700

Data Index: 3660811 (Open Web Text)

Max Activating Token Index: 9

Text #12

Max Range: 3.2915. Min Range: -3.2915

Max Act: 3.1445. Min Act: -0.1700

Data Index: 3809173 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 3.2915. Min Range: -3.2915

Max Act: 3.1478. Min Act: -0.1700

Data Index: 5499502 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 3.2915. Min Range: -3.2915

Max Act: 3.1434. Min Act: -0.1700

Data Index: 2353013 (Open Web Text)

Max Activating Token Index: 7

Text #15

Max Range: 3.2915. Min Range: -3.2915

Max Act: 3.1424. Min Act: -0.1700

Data Index: 1622978 (Open Web Text)

Max Activating Token Index: 8

Text #16

Max Range: 3.2915. Min Range: -3.2915

Max Act: 3.1445. Min Act: -0.1700

Data Index: 7114689 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 3.2915. Min Range: -3.2915

Max Act: 3.1478. Min Act: -0.1700

Data Index: 1857388 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 3.2915. Min Range: -3.2915

Max Act: 3.1287. Min Act: -0.1700

Data Index: 5690358 (Open Web Text)

Max Activating Token Index: 9

Text #19

Max Range: 3.2915. Min Range: -3.2915

Max Act: 3.1276. Min Act: -0.1700

Data Index: 281199 (Open Web Text)

Max Activating Token Index: 5