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

Dataset: Open Web Text

Neuron 2596 in Layer 1

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: 4.2834. Min Range: -4.2834

Max Act: 4.2834. Min Act: -0.1700

Data Index: 2010822 (Open Web Text)

Max Activating Token Index: 552

Text #1

Max Range: 4.2834. Min Range: -4.2834

Max Act: 4.2681. Min Act: -0.1700

Data Index: 5099584 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 4.2834. Min Range: -4.2834

Max Act: 4.2554. Min Act: -0.1700

Data Index: 3619320 (Open Web Text)

Max Activating Token Index: 55

Text #3

Max Range: 4.2834. Min Range: -4.2834

Max Act: 4.2209. Min Act: -0.1700

Data Index: 3531555 (Open Web Text)

Max Activating Token Index: 68

Text #4

Max Range: 4.2834. Min Range: -4.2834

Max Act: 4.1729. Min Act: -0.1700

Data Index: 3830282 (Open Web Text)

Max Activating Token Index: 466

Text #5

Max Range: 4.2834. Min Range: -4.2834

Max Act: 4.1892. Min Act: -0.1700

Data Index: 2645480 (Open Web Text)

Max Activating Token Index: 243

Text #6

Max Range: 4.2834. Min Range: -4.2834

Max Act: 4.2027. Min Act: -0.1700

Data Index: 6655082 (Open Web Text)

Max Activating Token Index: 7

Text #7

Max Range: 4.2834. Min Range: -4.2834

Max Act: 4.1928. Min Act: -0.1700

Data Index: 7318637 (Open Web Text)

Max Activating Token Index: 814

Text #8

Max Range: 4.2834. Min Range: -4.2834

Max Act: 4.1691. Min Act: -0.1700

Data Index: 3965024 (Open Web Text)

Max Activating Token Index: 959

Text #9

Max Range: 4.2834. Min Range: -4.2834

Max Act: 4.1623. Min Act: -0.1700

Data Index: 3852639 (Open Web Text)

Max Activating Token Index: 953

Text #10

Max Range: 4.2834. Min Range: -4.2834

Max Act: 4.1759. Min Act: -0.1700

Data Index: 3279230 (Open Web Text)

Max Activating Token Index: 107

Text #11

Max Range: 4.2834. Min Range: -4.2834

Max Act: 4.1828. Min Act: -0.1700

Data Index: 8547573 (Open Web Text)

Max Activating Token Index: 6

Text #12

Max Range: 4.2834. Min Range: -4.2834

Max Act: 4.1768. Min Act: -0.1700

Data Index: 7267418 (Open Web Text)

Max Activating Token Index: 14

Text #13

Max Range: 4.2834. Min Range: -4.2834

Max Act: 4.1596. Min Act: -0.1700

Data Index: 6536558 (Open Web Text)

Max Activating Token Index: 470

Text #14

Max Range: 4.2834. Min Range: -4.2834

Max Act: 4.1680. Min Act: -0.1700

Data Index: 6308912 (Open Web Text)

Max Activating Token Index: 614

Text #15

Max Range: 4.2834. Min Range: -4.2834

Max Act: 4.1756. Min Act: -0.1700

Data Index: 6139139 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 4.2834. Min Range: -4.2834

Max Act: 4.1544. Min Act: -0.1700

Data Index: 3945927 (Open Web Text)

Max Activating Token Index: 251

Text #17

Max Range: 4.2834. Min Range: -4.2834

Max Act: 4.1453. Min Act: -0.1700

Data Index: 3727325 (Open Web Text)

Max Activating Token Index: 456

Text #18

Max Range: 4.2834. Min Range: -4.2834

Max Act: 4.1549. Min Act: -0.1700

Data Index: 1645448 (Open Web Text)

Max Activating Token Index: 413

Text #19

Max Range: 4.2834. Min Range: -4.2834

Max Act: 4.1182. Min Act: -0.1700

Data Index: 74359 (Open Web Text)

Max Activating Token Index: 385