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

Dataset: Open Web Text

Neuron 125 in Layer 5

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: 3.1096. Min Range: -3.1096

Max Act: 3.1096. Min Act: -0.1700

Data Index: 8032779 (Open Web Text)

Max Activating Token Index: 943

Text #1

Max Range: 3.1096. Min Range: -3.1096

Max Act: 3.1021. Min Act: -0.1700

Data Index: 8688140 (Open Web Text)

Max Activating Token Index: 558

Text #2

Max Range: 3.1096. Min Range: -3.1096

Max Act: 3.0764. Min Act: -0.1700

Data Index: 6377427 (Open Web Text)

Max Activating Token Index: 125

Text #3

Max Range: 3.1096. Min Range: -3.1096

Max Act: 3.0117. Min Act: -0.1700

Data Index: 4151580 (Open Web Text)

Max Activating Token Index: 896

Text #4

Max Range: 3.1096. Min Range: -3.1096

Max Act: 2.9737. Min Act: -0.1700

Data Index: 3098675 (Open Web Text)

Max Activating Token Index: 684

Text #5

Max Range: 3.1096. Min Range: -3.1096

Max Act: 2.9591. Min Act: -0.1700

Data Index: 2610849 (Open Web Text)

Max Activating Token Index: 544

Text #6

Max Range: 3.1096. Min Range: -3.1096

Max Act: 2.9450. Min Act: -0.1700

Data Index: 8591184 (Open Web Text)

Max Activating Token Index: 545

Text #7

Max Range: 3.1096. Min Range: -3.1096

Max Act: 2.9604. Min Act: -0.1700

Data Index: 965175 (Open Web Text)

Max Activating Token Index: 428

Text #8

Max Range: 3.1096. Min Range: -3.1096

Max Act: 2.9577. Min Act: -0.1700

Data Index: 3372135 (Open Web Text)

Max Activating Token Index: 290

Text #9

Max Range: 3.1096. Min Range: -3.1096

Max Act: 2.9316. Min Act: -0.1700

Data Index: 4918986 (Open Web Text)

Max Activating Token Index: 793

Text #10

Max Range: 3.1096. Min Range: -3.1096

Max Act: 2.9072. Min Act: -0.1700

Data Index: 7776250 (Open Web Text)

Max Activating Token Index: 117

Text #11

Max Range: 3.1096. Min Range: -3.1096

Max Act: 2.9010. Min Act: -0.1700

Data Index: 1701339 (Open Web Text)

Max Activating Token Index: 822

Text #12

Max Range: 3.1096. Min Range: -3.1096

Max Act: 2.9012. Min Act: -0.1700

Data Index: 6491654 (Open Web Text)

Max Activating Token Index: 565

Text #13

Max Range: 3.1096. Min Range: -3.1096

Max Act: 2.8944. Min Act: -0.1700

Data Index: 7047872 (Open Web Text)

Max Activating Token Index: 447

Text #14

Max Range: 3.1096. Min Range: -3.1096

Max Act: 2.9016. Min Act: -0.1700

Data Index: 7020596 (Open Web Text)

Max Activating Token Index: 386

Text #15

Max Range: 3.1096. Min Range: -3.1096

Max Act: 2.8924. Min Act: -0.1700

Data Index: 8058593 (Open Web Text)

Max Activating Token Index: 311

Text #16

Max Range: 3.1096. Min Range: -3.1096

Max Act: 2.8874. Min Act: -0.1700

Data Index: 6487452 (Open Web Text)

Max Activating Token Index: 703

Text #17

Max Range: 3.1096. Min Range: -3.1096

Max Act: 2.8956. Min Act: -0.1700

Data Index: 2804388 (Open Web Text)

Max Activating Token Index: 568

Text #18

Max Range: 3.1096. Min Range: -3.1096

Max Act: 2.8975. Min Act: -0.1700

Data Index: 7761154 (Open Web Text)

Max Activating Token Index: 797

Text #19

Max Range: 3.1096. Min Range: -3.1096

Max Act: 2.8926. Min Act: -0.1700

Data Index: 1467109 (Open Web Text)

Max Activating Token Index: 627