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

Dataset: Open Web Text

Neuron 2994 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: 2.2072. Min Range: -2.2072

Max Act: 2.2072. Min Act: -0.1700

Data Index: 4323195 (Open Web Text)

Max Activating Token Index: 18

Text #1

Max Range: 2.2072. Min Range: -2.2072

Max Act: 2.1877. Min Act: -0.1700

Data Index: 2307532 (Open Web Text)

Max Activating Token Index: 21

Text #2

Max Range: 2.2072. Min Range: -2.2072

Max Act: 2.1715. Min Act: -0.1697

Data Index: 5877535 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 2.2072. Min Range: -2.2072

Max Act: 2.1656. Min Act: -0.1700

Data Index: 3772707 (Open Web Text)

Max Activating Token Index: 29

Text #4

Max Range: 2.2072. Min Range: -2.2072

Max Act: 2.1712. Min Act: -0.1700

Data Index: 6438005 (Open Web Text)

Max Activating Token Index: 15

Text #5

Max Range: 2.2072. Min Range: -2.2072

Max Act: 2.1690. Min Act: -0.1700

Data Index: 8384038 (Open Web Text)

Max Activating Token Index: 61

Text #6

Max Range: 2.2072. Min Range: -2.2072

Max Act: 2.1642. Min Act: -0.1700

Data Index: 4562293 (Open Web Text)

Max Activating Token Index: 355

Text #7

Max Range: 2.2072. Min Range: -2.2072

Max Act: 2.1673. Min Act: -0.1700

Data Index: 8476781 (Open Web Text)

Max Activating Token Index: 8

Text #8

Max Range: 2.2072. Min Range: -2.2072

Max Act: 2.1645. Min Act: -0.1700

Data Index: 2162465 (Open Web Text)

Max Activating Token Index: 54

Text #9

Max Range: 2.2072. Min Range: -2.2072

Max Act: 2.1766. Min Act: -0.1700

Data Index: 5077903 (Open Web Text)

Max Activating Token Index: 18

Text #10

Max Range: 2.2072. Min Range: -2.2072

Max Act: 2.1461. Min Act: -0.1700

Data Index: 1914729 (Open Web Text)

Max Activating Token Index: 27

Text #11

Max Range: 2.2072. Min Range: -2.2072

Max Act: 2.1507. Min Act: -0.1700

Data Index: 628808 (Open Web Text)

Max Activating Token Index: 209

Text #12

Max Range: 2.2072. Min Range: -2.2072

Max Act: 2.1365. Min Act: -0.1700

Data Index: 3641223 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 2.2072. Min Range: -2.2072

Max Act: 2.1340. Min Act: -0.1700

Data Index: 2388217 (Open Web Text)

Max Activating Token Index: 19

Text #14

Max Range: 2.2072. Min Range: -2.2072

Max Act: 2.1422. Min Act: -0.1700

Data Index: 3760235 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 2.2072. Min Range: -2.2072

Max Act: 2.1434. Min Act: -0.1700

Data Index: 5257652 (Open Web Text)

Max Activating Token Index: 9

Text #16

Max Range: 2.2072. Min Range: -2.2072

Max Act: 2.1441. Min Act: -0.1700

Data Index: 5679589 (Open Web Text)

Max Activating Token Index: 358

Text #17

Max Range: 2.2072. Min Range: -2.2072

Max Act: 2.1347. Min Act: -0.1700

Data Index: 83964 (Open Web Text)

Max Activating Token Index: 170

Text #18

Max Range: 2.2072. Min Range: -2.2072

Max Act: 2.1272. Min Act: -0.1700

Data Index: 4569418 (Open Web Text)

Max Activating Token Index: 10

Text #19

Max Range: 2.2072. Min Range: -2.2072

Max Act: 2.1407. Min Act: -0.1700

Data Index: 5813197 (Open Web Text)

Max Activating Token Index: 58