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

Dataset: Open Web Text

Neuron 1119 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: 1.5916. Min Range: -1.5916

Max Act: 1.5916. Min Act: -0.1700

Data Index: 8709181 (Open Web Text)

Max Activating Token Index: 536

Text #1

Max Range: 1.5916. Min Range: -1.5916

Max Act: 1.5039. Min Act: -0.1700

Data Index: 8223120 (Open Web Text)

Max Activating Token Index: 691

Text #2

Max Range: 1.5916. Min Range: -1.5916

Max Act: 1.4805. Min Act: -0.1700

Data Index: 1541305 (Open Web Text)

Max Activating Token Index: 554

Text #3

Max Range: 1.5916. Min Range: -1.5916

Max Act: 1.4907. Min Act: -0.1700

Data Index: 7410497 (Open Web Text)

Max Activating Token Index: 121

Text #4

Max Range: 1.5916. Min Range: -1.5916

Max Act: 1.4878. Min Act: -0.1700

Data Index: 5419497 (Open Web Text)

Max Activating Token Index: 199

Text #5

Max Range: 1.5916. Min Range: -1.5916

Max Act: 1.4901. Min Act: -0.1700

Data Index: 7874382 (Open Web Text)

Max Activating Token Index: 594

Text #6

Max Range: 1.5916. Min Range: -1.5916

Max Act: 1.4790. Min Act: -0.1700

Data Index: 6948235 (Open Web Text)

Max Activating Token Index: 573

Text #7

Max Range: 1.5916. Min Range: -1.5916

Max Act: 1.4737. Min Act: -0.1700

Data Index: 8722223 (Open Web Text)

Max Activating Token Index: 835

Text #8

Max Range: 1.5916. Min Range: -1.5916

Max Act: 1.4738. Min Act: -0.1700

Data Index: 8699270 (Open Web Text)

Max Activating Token Index: 133

Text #9

Max Range: 1.5916. Min Range: -1.5916

Max Act: 1.4710. Min Act: -0.1700

Data Index: 3105075 (Open Web Text)

Max Activating Token Index: 472

Text #10

Max Range: 1.5916. Min Range: -1.5916

Max Act: 1.4657. Min Act: -0.1700

Data Index: 3380732 (Open Web Text)

Max Activating Token Index: 666

Text #11

Max Range: 1.5916. Min Range: -1.5916

Max Act: 1.4586. Min Act: -0.1700

Data Index: 880059 (Open Web Text)

Max Activating Token Index: 577

Text #12

Max Range: 1.5916. Min Range: -1.5916

Max Act: 1.4613. Min Act: -0.1700

Data Index: 1256321 (Open Web Text)

Max Activating Token Index: 589

Text #13

Max Range: 1.5916. Min Range: -1.5916

Max Act: 1.4620. Min Act: -0.1700

Data Index: 2275751 (Open Web Text)

Max Activating Token Index: 432

Text #14

Max Range: 1.5916. Min Range: -1.5916

Max Act: 1.4613. Min Act: -0.1700

Data Index: 6883382 (Open Web Text)

Max Activating Token Index: 707

Text #15

Max Range: 1.5916. Min Range: -1.5916

Max Act: 1.4624. Min Act: -0.1700

Data Index: 3150960 (Open Web Text)

Max Activating Token Index: 465

Text #16

Max Range: 1.5916. Min Range: -1.5916

Max Act: 1.4497. Min Act: -0.1700

Data Index: 8034876 (Open Web Text)

Max Activating Token Index: 578

Text #17

Max Range: 1.5916. Min Range: -1.5916

Max Act: 1.4557. Min Act: -0.1700

Data Index: 5345937 (Open Web Text)

Max Activating Token Index: 338

Text #18

Max Range: 1.5916. Min Range: -1.5916

Max Act: 1.4440. Min Act: -0.1700

Data Index: 1416522 (Open Web Text)

Max Activating Token Index: 561

Text #19

Max Range: 1.5916. Min Range: -1.5916

Max Act: 1.4498. Min Act: -0.1700

Data Index: 4790213 (Open Web Text)

Max Activating Token Index: 206