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

Dataset: Open Web Text

Neuron 2826 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: 4.0748. Min Range: -4.0748

Max Act: 4.0748. Min Act: -0.1700

Data Index: 889741 (Open Web Text)

Max Activating Token Index: 284

Text #1

Max Range: 4.0748. Min Range: -4.0748

Max Act: 4.0723. Min Act: -0.1700

Data Index: 7243151 (Open Web Text)

Max Activating Token Index: 516

Text #2

Max Range: 4.0748. Min Range: -4.0748

Max Act: 4.0305. Min Act: -0.1700

Data Index: 7467409 (Open Web Text)

Max Activating Token Index: 300

Text #3

Max Range: 4.0748. Min Range: -4.0748

Max Act: 4.0307. Min Act: -0.1700

Data Index: 7160160 (Open Web Text)

Max Activating Token Index: 585

Text #4

Max Range: 4.0748. Min Range: -4.0748

Max Act: 4.0393. Min Act: -0.1700

Data Index: 4674656 (Open Web Text)

Max Activating Token Index: 966

Text #5

Max Range: 4.0748. Min Range: -4.0748

Max Act: 3.9727. Min Act: -0.1700

Data Index: 469023 (Open Web Text)

Max Activating Token Index: 27

Text #6

Max Range: 4.0748. Min Range: -4.0748

Max Act: 3.9818. Min Act: -0.1700

Data Index: 947022 (Open Web Text)

Max Activating Token Index: 369

Text #7

Max Range: 4.0748. Min Range: -4.0748

Max Act: 3.9569. Min Act: -0.1700

Data Index: 7292278 (Open Web Text)

Max Activating Token Index: 929

Text #8

Max Range: 4.0748. Min Range: -4.0748

Max Act: 3.9322. Min Act: -0.1700

Data Index: 6127560 (Open Web Text)

Max Activating Token Index: 119

Text #9

Max Range: 4.0748. Min Range: -4.0748

Max Act: 3.9063. Min Act: -0.1700

Data Index: 8772077 (Open Web Text)

Max Activating Token Index: 828

Text #10

Max Range: 4.0748. Min Range: -4.0748

Max Act: 3.8753. Min Act: -0.1700

Data Index: 5695025 (Open Web Text)

Max Activating Token Index: 152

Text #11

Max Range: 4.0748. Min Range: -4.0748

Max Act: 3.9042. Min Act: -0.1700

Data Index: 7304894 (Open Web Text)

Max Activating Token Index: 501

Text #12

Max Range: 4.0748. Min Range: -4.0748

Max Act: 3.8878. Min Act: -0.1700

Data Index: 8725609 (Open Web Text)

Max Activating Token Index: 270

Text #13

Max Range: 4.0748. Min Range: -4.0748

Max Act: 3.8896. Min Act: -0.1700

Data Index: 6677809 (Open Web Text)

Max Activating Token Index: 633

Text #14

Max Range: 4.0748. Min Range: -4.0748

Max Act: 3.8823. Min Act: -0.1700

Data Index: 2430548 (Open Web Text)

Max Activating Token Index: 785

Text #15

Max Range: 4.0748. Min Range: -4.0748

Max Act: 3.8737. Min Act: -0.1700

Data Index: 8544107 (Open Web Text)

Max Activating Token Index: 992

Text #16

Max Range: 4.0748. Min Range: -4.0748

Max Act: 3.8532. Min Act: -0.1700

Data Index: 832432 (Open Web Text)

Max Activating Token Index: 372

Text #17

Max Range: 4.0748. Min Range: -4.0748

Max Act: 3.8493. Min Act: -0.1700

Data Index: 671815 (Open Web Text)

Max Activating Token Index: 670

Text #18

Max Range: 4.0748. Min Range: -4.0748

Max Act: 3.8531. Min Act: -0.1700

Data Index: 2636333 (Open Web Text)

Max Activating Token Index: 924

Text #19

Max Range: 4.0748. Min Range: -4.0748

Max Act: 3.8562. Min Act: -0.1700

Data Index: 2077511 (Open Web Text)

Max Activating Token Index: 752