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

Dataset: Open Web Text

Neuron 639 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: 1.7566. Min Range: -1.7566

Max Act: 1.7566. Min Act: -0.1700

Data Index: 3058822 (Open Web Text)

Max Activating Token Index: 80

Text #1

Max Range: 1.7566. Min Range: -1.7566

Max Act: 1.7181. Min Act: -0.1700

Data Index: 3243001 (Open Web Text)

Max Activating Token Index: 451

Text #2

Max Range: 1.7566. Min Range: -1.7566

Max Act: 1.7073. Min Act: -0.1700

Data Index: 5317703 (Open Web Text)

Max Activating Token Index: 24

Text #3

Max Range: 1.7566. Min Range: -1.7566

Max Act: 1.7110. Min Act: -0.1697

Data Index: 2602823 (Open Web Text)

Max Activating Token Index: 160

Text #4

Max Range: 1.7566. Min Range: -1.7566

Max Act: 1.6993. Min Act: -0.1700

Data Index: 1063286 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 1.7566. Min Range: -1.7566

Max Act: 1.7023. Min Act: -0.1700

Data Index: 5048543 (Open Web Text)

Max Activating Token Index: 41

Text #6

Max Range: 1.7566. Min Range: -1.7566

Max Act: 1.7102. Min Act: -0.1700

Data Index: 4611345 (Open Web Text)

Max Activating Token Index: 599

Text #7

Max Range: 1.7566. Min Range: -1.7566

Max Act: 1.6903. Min Act: -0.1699

Data Index: 8378040 (Open Web Text)

Max Activating Token Index: 24

Text #8

Max Range: 1.7566. Min Range: -1.7566

Max Act: 1.6967. Min Act: -0.1700

Data Index: 4171204 (Open Web Text)

Max Activating Token Index: 125

Text #9

Max Range: 1.7566. Min Range: -1.7566

Max Act: 1.6957. Min Act: -0.1700

Data Index: 4176602 (Open Web Text)

Max Activating Token Index: 10

Text #10

Max Range: 1.7566. Min Range: -1.7566

Max Act: 1.6970. Min Act: -0.1700

Data Index: 1824671 (Open Web Text)

Max Activating Token Index: 32

Text #11

Max Range: 1.7566. Min Range: -1.7566

Max Act: 1.6988. Min Act: -0.1700

Data Index: 1089354 (Open Web Text)

Max Activating Token Index: 527

Text #12

Max Range: 1.7566. Min Range: -1.7566

Max Act: 1.6895. Min Act: -0.1700

Data Index: 2504570 (Open Web Text)

Max Activating Token Index: 117

Text #13

Max Range: 1.7566. Min Range: -1.7566

Max Act: 1.6793. Min Act: -0.1700

Data Index: 7540146 (Open Web Text)

Max Activating Token Index: 16

Text #14

Max Range: 1.7566. Min Range: -1.7566

Max Act: 1.6822. Min Act: -0.1700

Data Index: 6405615 (Open Web Text)

Max Activating Token Index: 10

Text #15

Max Range: 1.7566. Min Range: -1.7566

Max Act: 1.6873. Min Act: -0.1700

Data Index: 3241238 (Open Web Text)

Max Activating Token Index: 413

Text #16

Max Range: 1.7566. Min Range: -1.7566

Max Act: 1.6764. Min Act: -0.1700

Data Index: 8368880 (Open Web Text)

Max Activating Token Index: 600

Text #17

Max Range: 1.7566. Min Range: -1.7566

Max Act: 1.6694. Min Act: -0.1700

Data Index: 4755116 (Open Web Text)

Max Activating Token Index: 488

Text #18

Max Range: 1.7566. Min Range: -1.7566

Max Act: 1.6702. Min Act: -0.1700

Data Index: 4493784 (Open Web Text)

Max Activating Token Index: 553

Text #19

Max Range: 1.7566. Min Range: -1.7566

Max Act: 1.6691. Min Act: -0.1700

Data Index: 977299 (Open Web Text)

Max Activating Token Index: 54