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

Dataset: Open Web Text

Neuron 1590 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: 4.5632. Min Range: -4.5632

Max Act: 4.5632. Min Act: -0.1697

Data Index: 8162051 (Open Web Text)

Max Activating Token Index: 399

Text #1

Max Range: 4.5632. Min Range: -4.5632

Max Act: 4.4806. Min Act: -0.1699

Data Index: 2588396 (Open Web Text)

Max Activating Token Index: 172

Text #2

Max Range: 4.5632. Min Range: -4.5632

Max Act: 4.4195. Min Act: -0.1700

Data Index: 413086 (Open Web Text)

Max Activating Token Index: 45

Text #3

Max Range: 4.5632. Min Range: -4.5632

Max Act: 4.3304. Min Act: -0.1700

Data Index: 3668085 (Open Web Text)

Max Activating Token Index: 20

Text #4

Max Range: 4.5632. Min Range: -4.5632

Max Act: 4.3265. Min Act: -0.1700

Data Index: 7639232 (Open Web Text)

Max Activating Token Index: 71

Text #5

Max Range: 4.5632. Min Range: -4.5632

Max Act: 4.3049. Min Act: -0.1700

Data Index: 3617918 (Open Web Text)

Max Activating Token Index: 18

Text #6

Max Range: 4.5632. Min Range: -4.5632

Max Act: 4.1635. Min Act: -0.1700

Data Index: 5939965 (Open Web Text)

Max Activating Token Index: 57

Text #7

Max Range: 4.5632. Min Range: -4.5632

Max Act: 4.1612. Min Act: -0.1700

Data Index: 7510211 (Open Web Text)

Max Activating Token Index: 502

Text #8

Max Range: 4.5632. Min Range: -4.5632

Max Act: 4.1247. Min Act: -0.1700

Data Index: 3030505 (Open Web Text)

Max Activating Token Index: 41

Text #9

Max Range: 4.5632. Min Range: -4.5632

Max Act: 4.0890. Min Act: -0.1700

Data Index: 5956326 (Open Web Text)

Max Activating Token Index: 50

Text #10

Max Range: 4.5632. Min Range: -4.5632

Max Act: 4.1008. Min Act: -0.1700

Data Index: 5818632 (Open Web Text)

Max Activating Token Index: 35

Text #11

Max Range: 4.5632. Min Range: -4.5632

Max Act: 4.1231. Min Act: -0.1700

Data Index: 5440000 (Open Web Text)

Max Activating Token Index: 486

Text #12

Max Range: 4.5632. Min Range: -4.5632

Max Act: 4.0839. Min Act: -0.1700

Data Index: 3547760 (Open Web Text)

Max Activating Token Index: 24

Text #13

Max Range: 4.5632. Min Range: -4.5632

Max Act: 4.0754. Min Act: -0.1700

Data Index: 3430978 (Open Web Text)

Max Activating Token Index: 779

Text #14

Max Range: 4.5632. Min Range: -4.5632

Max Act: 4.0695. Min Act: -0.1700

Data Index: 6244591 (Open Web Text)

Max Activating Token Index: 476

Text #15

Max Range: 4.5632. Min Range: -4.5632

Max Act: 4.0730. Min Act: -0.1700

Data Index: 708565 (Open Web Text)

Max Activating Token Index: 67

Text #16

Max Range: 4.5632. Min Range: -4.5632

Max Act: 4.0721. Min Act: -0.1700

Data Index: 4056422 (Open Web Text)

Max Activating Token Index: 124

Text #17

Max Range: 4.5632. Min Range: -4.5632

Max Act: 4.0552. Min Act: -0.1700

Data Index: 731406 (Open Web Text)

Max Activating Token Index: 447

Text #18

Max Range: 4.5632. Min Range: -4.5632

Max Act: 4.0503. Min Act: -0.1700

Data Index: 3560915 (Open Web Text)

Max Activating Token Index: 16

Text #19

Max Range: 4.5632. Min Range: -4.5632

Max Act: 4.0361. Min Act: -0.1699

Data Index: 413085 (Open Web Text)

Max Activating Token Index: 171