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

Dataset: Open Web Text

Neuron 1963 in Layer 4

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: 3.2523. Min Range: -3.2523

Max Act: 3.2523. Min Act: -0.1700

Data Index: 2988877 (Open Web Text)

Max Activating Token Index: 107

Text #1

Max Range: 3.2523. Min Range: -3.2523

Max Act: 3.1975. Min Act: -0.1700

Data Index: 2024348 (Open Web Text)

Max Activating Token Index: 395

Text #2

Max Range: 3.2523. Min Range: -3.2523

Max Act: 3.1919. Min Act: -0.1700

Data Index: 3972218 (Open Web Text)

Max Activating Token Index: 797

Text #3

Max Range: 3.2523. Min Range: -3.2523

Max Act: 3.0503. Min Act: -0.1700

Data Index: 5823590 (Open Web Text)

Max Activating Token Index: 17

Text #4

Max Range: 3.2523. Min Range: -3.2523

Max Act: 3.0246. Min Act: -0.1700

Data Index: 8195631 (Open Web Text)

Max Activating Token Index: 267

Text #5

Max Range: 3.2523. Min Range: -3.2523

Max Act: 3.0028. Min Act: -0.1700

Data Index: 6075220 (Open Web Text)

Max Activating Token Index: 460

Text #6

Max Range: 3.2523. Min Range: -3.2523

Max Act: 3.0143. Min Act: -0.1700

Data Index: 5782649 (Open Web Text)

Max Activating Token Index: 97

Text #7

Max Range: 3.2523. Min Range: -3.2523

Max Act: 3.0254. Min Act: -0.1700

Data Index: 6669969 (Open Web Text)

Max Activating Token Index: 776

Text #8

Max Range: 3.2523. Min Range: -3.2523

Max Act: 2.9987. Min Act: -0.1700

Data Index: 5614217 (Open Web Text)

Max Activating Token Index: 431

Text #9

Max Range: 3.2523. Min Range: -3.2523

Max Act: 2.9409. Min Act: -0.1700

Data Index: 6033775 (Open Web Text)

Max Activating Token Index: 956

Text #10

Max Range: 3.2523. Min Range: -3.2523

Max Act: 2.9941. Min Act: -0.1700

Data Index: 2403215 (Open Web Text)

Max Activating Token Index: 769

Text #11

Max Range: 3.2523. Min Range: -3.2523

Max Act: 3.0058. Min Act: -0.1700

Data Index: 7154867 (Open Web Text)

Max Activating Token Index: 710

Text #12

Max Range: 3.2523. Min Range: -3.2523

Max Act: 2.9833. Min Act: -0.1700

Data Index: 8181949 (Open Web Text)

Max Activating Token Index: 386

Text #13

Max Range: 3.2523. Min Range: -3.2523

Max Act: 3.0231. Min Act: -0.1700

Data Index: 1088310 (Open Web Text)

Max Activating Token Index: 316

Text #14

Max Range: 3.2523. Min Range: -3.2523

Max Act: 3.0114. Min Act: -0.1700

Data Index: 1479515 (Open Web Text)

Max Activating Token Index: 70

Text #15

Max Range: 3.2523. Min Range: -3.2523

Max Act: 2.9697. Min Act: -0.1700

Data Index: 4833337 (Open Web Text)

Max Activating Token Index: 796

Text #16

Max Range: 3.2523. Min Range: -3.2523

Max Act: 2.9529. Min Act: -0.1700

Data Index: 2970631 (Open Web Text)

Max Activating Token Index: 880

Text #17

Max Range: 3.2523. Min Range: -3.2523

Max Act: 2.9127. Min Act: -0.1700

Data Index: 4123220 (Open Web Text)

Max Activating Token Index: 487

Text #18

Max Range: 3.2523. Min Range: -3.2523

Max Act: 2.9696. Min Act: -0.1700

Data Index: 3178637 (Open Web Text)

Max Activating Token Index: 721

Text #19

Max Range: 3.2523. Min Range: -3.2523

Max Act: 2.9331. Min Act: -0.1700

Data Index: 1409919 (Open Web Text)

Max Activating Token Index: 664