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

Dataset: Open Web Text

Neuron 1008 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: 0.6923. Min Range: -0.6923

Max Act: 0.6923. Min Act: -0.1681

Data Index: 6348242 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.6425. Min Act: -0.1653

Data Index: 1707009 (Open Web Text)

Max Activating Token Index: 2

Text #2

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.6265. Min Act: -0.1694

Data Index: 3064984 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.6199. Min Act: -0.1686

Data Index: 8119704 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.6158. Min Act: -0.1699

Data Index: 2595115 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.6166. Min Act: -0.1700

Data Index: 2373600 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.6149. Min Act: -0.1681

Data Index: 8043509 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.6149. Min Act: -0.1700

Data Index: 3678571 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.6149. Min Act: -0.1694

Data Index: 7654658 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.6149. Min Act: -0.1644

Data Index: 5757950 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.6149. Min Act: -0.1681

Data Index: 595100 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.6149. Min Act: -0.1700

Data Index: 1346980 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.6149. Min Act: -0.1692

Data Index: 7660366 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.6149. Min Act: -0.1699

Data Index: 5743316 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.6166. Min Act: -0.1682

Data Index: 8564912 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.6082. Min Act: -0.1699

Data Index: 3049493 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.6057. Min Act: -0.1662

Data Index: 3640325 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.6126. Min Act: -0.1693

Data Index: 3743483 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.5956. Min Act: -0.1675

Data Index: 2507844 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 0.6923. Min Range: -0.6923

Max Act: 0.5917. Min Act: -0.1690

Data Index: 7398263 (Open Web Text)

Max Activating Token Index: 3