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

Dataset: Open Web Text

Neuron 2561 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: 1.4462. Min Range: -1.4462

Max Act: 1.4462. Min Act: -0.1700

Data Index: 5843414 (Open Web Text)

Max Activating Token Index: 464

Text #1

Max Range: 1.4462. Min Range: -1.4462

Max Act: 1.4424. Min Act: -0.1700

Data Index: 685842 (Open Web Text)

Max Activating Token Index: 977

Text #2

Max Range: 1.4462. Min Range: -1.4462

Max Act: 1.4236. Min Act: -0.1700

Data Index: 4075622 (Open Web Text)

Max Activating Token Index: 889

Text #3

Max Range: 1.4462. Min Range: -1.4462

Max Act: 1.4089. Min Act: -0.1700

Data Index: 3981558 (Open Web Text)

Max Activating Token Index: 633

Text #4

Max Range: 1.4462. Min Range: -1.4462

Max Act: 1.4041. Min Act: -0.1699

Data Index: 2466883 (Open Web Text)

Max Activating Token Index: 628

Text #5

Max Range: 1.4462. Min Range: -1.4462

Max Act: 1.3960. Min Act: -0.1700

Data Index: 5889149 (Open Web Text)

Max Activating Token Index: 305

Text #6

Max Range: 1.4462. Min Range: -1.4462

Max Act: 1.4112. Min Act: -0.1700

Data Index: 4083567 (Open Web Text)

Max Activating Token Index: 235

Text #7

Max Range: 1.4462. Min Range: -1.4462

Max Act: 1.4013. Min Act: -0.1700

Data Index: 250241 (Open Web Text)

Max Activating Token Index: 155

Text #8

Max Range: 1.4462. Min Range: -1.4462

Max Act: 1.4059. Min Act: -0.1700

Data Index: 8267496 (Open Web Text)

Max Activating Token Index: 983

Text #9

Max Range: 1.4462. Min Range: -1.4462

Max Act: 1.3883. Min Act: -0.1700

Data Index: 4809352 (Open Web Text)

Max Activating Token Index: 481

Text #10

Max Range: 1.4462. Min Range: -1.4462

Max Act: 1.3872. Min Act: -0.1700

Data Index: 3843757 (Open Web Text)

Max Activating Token Index: 219

Text #11

Max Range: 1.4462. Min Range: -1.4462

Max Act: 1.3839. Min Act: -0.1700

Data Index: 3128756 (Open Web Text)

Max Activating Token Index: 267

Text #12

Max Range: 1.4462. Min Range: -1.4462

Max Act: 1.3807. Min Act: -0.1699

Data Index: 922935 (Open Web Text)

Max Activating Token Index: 984

Text #13

Max Range: 1.4462. Min Range: -1.4462

Max Act: 1.3817. Min Act: -0.1700

Data Index: 8267497 (Open Web Text)

Max Activating Token Index: 518

Text #14

Max Range: 1.4462. Min Range: -1.4462

Max Act: 1.3792. Min Act: -0.1700

Data Index: 2791351 (Open Web Text)

Max Activating Token Index: 256

Text #15

Max Range: 1.4462. Min Range: -1.4462

Max Act: 1.3762. Min Act: -0.1700

Data Index: 3044126 (Open Web Text)

Max Activating Token Index: 466

Text #16

Max Range: 1.4462. Min Range: -1.4462

Max Act: 1.3744. Min Act: -0.1700

Data Index: 1221860 (Open Web Text)

Max Activating Token Index: 90

Text #17

Max Range: 1.4462. Min Range: -1.4462

Max Act: 1.3764. Min Act: -0.1699

Data Index: 7529800 (Open Web Text)

Max Activating Token Index: 581

Text #18

Max Range: 1.4462. Min Range: -1.4462

Max Act: 1.3744. Min Act: -0.1700

Data Index: 6636918 (Open Web Text)

Max Activating Token Index: 574

Text #19

Max Range: 1.4462. Min Range: -1.4462

Max Act: 1.3737. Min Act: -0.1700

Data Index: 1759871 (Open Web Text)

Max Activating Token Index: 204