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

Dataset: Open Web Text

Neuron 1274 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: 3.7990. Min Range: -3.7990

Max Act: 3.7937. Min Act: -0.1700

Data Index: 3843899 (Open Web Text)

Max Activating Token Index: 337

Text #1

Max Range: 3.7990. Min Range: -3.7990

Max Act: 3.7990. Min Act: -0.1700

Data Index: 5819511 (Open Web Text)

Max Activating Token Index: 825

Text #2

Max Range: 3.7990. Min Range: -3.7990

Max Act: 3.7689. Min Act: -0.1700

Data Index: 2084015 (Open Web Text)

Max Activating Token Index: 610

Text #3

Max Range: 3.7990. Min Range: -3.7990

Max Act: 3.7425. Min Act: -0.1700

Data Index: 479676 (Open Web Text)

Max Activating Token Index: 137

Text #4

Max Range: 3.7990. Min Range: -3.7990

Max Act: 3.7383. Min Act: -0.1700

Data Index: 6874859 (Open Web Text)

Max Activating Token Index: 189

Text #5

Max Range: 3.7990. Min Range: -3.7990

Max Act: 3.7458. Min Act: -0.1700

Data Index: 1180237 (Open Web Text)

Max Activating Token Index: 71

Text #6

Max Range: 3.7990. Min Range: -3.7990

Max Act: 3.6960. Min Act: -0.1700

Data Index: 799587 (Open Web Text)

Max Activating Token Index: 572

Text #7

Max Range: 3.7990. Min Range: -3.7990

Max Act: 3.6920. Min Act: -0.1700

Data Index: 27827 (Open Web Text)

Max Activating Token Index: 471

Text #8

Max Range: 3.7990. Min Range: -3.7990

Max Act: 3.6965. Min Act: -0.1700

Data Index: 5517073 (Open Web Text)

Max Activating Token Index: 585

Text #9

Max Range: 3.7990. Min Range: -3.7990

Max Act: 3.7019. Min Act: -0.1700

Data Index: 5940368 (Open Web Text)

Max Activating Token Index: 530

Text #10

Max Range: 3.7990. Min Range: -3.7990

Max Act: 3.7082. Min Act: -0.1700

Data Index: 765238 (Open Web Text)

Max Activating Token Index: 299

Text #11

Max Range: 3.7990. Min Range: -3.7990

Max Act: 3.7064. Min Act: -0.1700

Data Index: 303958 (Open Web Text)

Max Activating Token Index: 139

Text #12

Max Range: 3.7990. Min Range: -3.7990

Max Act: 3.6900. Min Act: -0.1700

Data Index: 2100701 (Open Web Text)

Max Activating Token Index: 255

Text #13

Max Range: 3.7990. Min Range: -3.7990

Max Act: 3.6723. Min Act: -0.1700

Data Index: 718068 (Open Web Text)

Max Activating Token Index: 110

Text #14

Max Range: 3.7990. Min Range: -3.7990

Max Act: 3.6736. Min Act: -0.1700

Data Index: 2691801 (Open Web Text)

Max Activating Token Index: 531

Text #15

Max Range: 3.7990. Min Range: -3.7990

Max Act: 3.6664. Min Act: -0.1700

Data Index: 1140974 (Open Web Text)

Max Activating Token Index: 164

Text #16

Max Range: 3.7990. Min Range: -3.7990

Max Act: 3.6717. Min Act: -0.1700

Data Index: 2569149 (Open Web Text)

Max Activating Token Index: 278

Text #17

Max Range: 3.7990. Min Range: -3.7990

Max Act: 3.6899. Min Act: -0.1700

Data Index: 583880 (Open Web Text)

Max Activating Token Index: 590

Text #18

Max Range: 3.7990. Min Range: -3.7990

Max Act: 3.6753. Min Act: -0.1700

Data Index: 2001698 (Open Web Text)

Max Activating Token Index: 335

Text #19

Max Range: 3.7990. Min Range: -3.7990

Max Act: 3.6795. Min Act: -0.1700

Data Index: 1895957 (Open Web Text)

Max Activating Token Index: 128