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

Dataset: Open Web Text

Neuron 2522 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: 1.7531. Min Range: -1.7531

Max Act: 1.7531. Min Act: -0.1700

Data Index: 3554483 (Open Web Text)

Max Activating Token Index: 507

Text #1

Max Range: 1.7531. Min Range: -1.7531

Max Act: 1.7455. Min Act: -0.1700

Data Index: 5889888 (Open Web Text)

Max Activating Token Index: 526

Text #2

Max Range: 1.7531. Min Range: -1.7531

Max Act: 1.7347. Min Act: -0.1700

Data Index: 2360126 (Open Web Text)

Max Activating Token Index: 305

Text #3

Max Range: 1.7531. Min Range: -1.7531

Max Act: 1.7284. Min Act: -0.1700

Data Index: 8081196 (Open Web Text)

Max Activating Token Index: 1005

Text #4

Max Range: 1.7531. Min Range: -1.7531

Max Act: 1.7218. Min Act: -0.1698

Data Index: 3026580 (Open Web Text)

Max Activating Token Index: 554

Text #5

Max Range: 1.7531. Min Range: -1.7531

Max Act: 1.7158. Min Act: -0.1700

Data Index: 5011256 (Open Web Text)

Max Activating Token Index: 725

Text #6

Max Range: 1.7531. Min Range: -1.7531

Max Act: 1.7275. Min Act: -0.1700

Data Index: 4938081 (Open Web Text)

Max Activating Token Index: 420

Text #7

Max Range: 1.7531. Min Range: -1.7531

Max Act: 1.7259. Min Act: -0.1700

Data Index: 2643630 (Open Web Text)

Max Activating Token Index: 855

Text #8

Max Range: 1.7531. Min Range: -1.7531

Max Act: 1.7026. Min Act: -0.1700

Data Index: 4847742 (Open Web Text)

Max Activating Token Index: 458

Text #9

Max Range: 1.7531. Min Range: -1.7531

Max Act: 1.7299. Min Act: -0.1700

Data Index: 8537260 (Open Web Text)

Max Activating Token Index: 799

Text #10

Max Range: 1.7531. Min Range: -1.7531

Max Act: 1.7082. Min Act: -0.1700

Data Index: 81116 (Open Web Text)

Max Activating Token Index: 582

Text #11

Max Range: 1.7531. Min Range: -1.7531

Max Act: 1.6920. Min Act: -0.1690

Data Index: 4938080 (Open Web Text)

Max Activating Token Index: 251

Text #12

Max Range: 1.7531. Min Range: -1.7531

Max Act: 1.6796. Min Act: -0.1700

Data Index: 81113 (Open Web Text)

Max Activating Token Index: 597

Text #13

Max Range: 1.7531. Min Range: -1.7531

Max Act: 1.6823. Min Act: -0.1700

Data Index: 4938078 (Open Web Text)

Max Activating Token Index: 595

Text #14

Max Range: 1.7531. Min Range: -1.7531

Max Act: 1.6713. Min Act: -0.1700

Data Index: 2452542 (Open Web Text)

Max Activating Token Index: 252

Text #15

Max Range: 1.7531. Min Range: -1.7531

Max Act: 1.6821. Min Act: -0.1700

Data Index: 5945314 (Open Web Text)

Max Activating Token Index: 630

Text #16

Max Range: 1.7531. Min Range: -1.7531

Max Act: 1.6734. Min Act: -0.1700

Data Index: 7413620 (Open Web Text)

Max Activating Token Index: 914

Text #17

Max Range: 1.7531. Min Range: -1.7531

Max Act: 1.6707. Min Act: -0.1700

Data Index: 3736090 (Open Web Text)

Max Activating Token Index: 537

Text #18

Max Range: 1.7531. Min Range: -1.7531

Max Act: 1.6831. Min Act: -0.1698

Data Index: 6208573 (Open Web Text)

Max Activating Token Index: 757

Text #19

Max Range: 1.7531. Min Range: -1.7531

Max Act: 1.6675. Min Act: -0.1700

Data Index: 2591265 (Open Web Text)

Max Activating Token Index: 549