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

Dataset: Open Web Text

Neuron 1988 in Layer 6

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: 5.3935. Min Range: -5.3935

Max Act: 5.3935. Min Act: -0.1700

Data Index: 3672812 (Open Web Text)

Max Activating Token Index: 684

Text #1

Max Range: 5.3935. Min Range: -5.3935

Max Act: 5.3551. Min Act: -0.1700

Data Index: 3929851 (Open Web Text)

Max Activating Token Index: 795

Text #2

Max Range: 5.3935. Min Range: -5.3935

Max Act: 5.3645. Min Act: -0.1700

Data Index: 5600839 (Open Web Text)

Max Activating Token Index: 894

Text #3

Max Range: 5.3935. Min Range: -5.3935

Max Act: 5.3193. Min Act: -0.1700

Data Index: 7955826 (Open Web Text)

Max Activating Token Index: 332

Text #4

Max Range: 5.3935. Min Range: -5.3935

Max Act: 5.2280. Min Act: -0.1700

Data Index: 4947069 (Open Web Text)

Max Activating Token Index: 317

Text #5

Max Range: 5.3935. Min Range: -5.3935

Max Act: 5.1850. Min Act: -0.1700

Data Index: 6534333 (Open Web Text)

Max Activating Token Index: 270

Text #6

Max Range: 5.3935. Min Range: -5.3935

Max Act: 5.1416. Min Act: -0.1700

Data Index: 4092879 (Open Web Text)

Max Activating Token Index: 343

Text #7

Max Range: 5.3935. Min Range: -5.3935

Max Act: 5.1321. Min Act: -0.1700

Data Index: 8394278 (Open Web Text)

Max Activating Token Index: 201

Text #8

Max Range: 5.3935. Min Range: -5.3935

Max Act: 5.0763. Min Act: -0.1700

Data Index: 356988 (Open Web Text)

Max Activating Token Index: 624

Text #9

Max Range: 5.3935. Min Range: -5.3935

Max Act: 5.0541. Min Act: -0.1700

Data Index: 3494129 (Open Web Text)

Max Activating Token Index: 1014

Text #10

Max Range: 5.3935. Min Range: -5.3935

Max Act: 5.1094. Min Act: -0.1700

Data Index: 8807581 (Open Web Text)

Max Activating Token Index: 749

Text #11

Max Range: 5.3935. Min Range: -5.3935

Max Act: 5.0700. Min Act: -0.1700

Data Index: 8598921 (Open Web Text)

Max Activating Token Index: 94

Text #12

Max Range: 5.3935. Min Range: -5.3935

Max Act: 5.0684. Min Act: -0.1700

Data Index: 3848030 (Open Web Text)

Max Activating Token Index: 946

Text #13

Max Range: 5.3935. Min Range: -5.3935

Max Act: 5.0444. Min Act: -0.1700

Data Index: 6439726 (Open Web Text)

Max Activating Token Index: 641

Text #14

Max Range: 5.3935. Min Range: -5.3935

Max Act: 5.0471. Min Act: -0.1700

Data Index: 3056663 (Open Web Text)

Max Activating Token Index: 677

Text #15

Max Range: 5.3935. Min Range: -5.3935

Max Act: 5.0581. Min Act: -0.1700

Data Index: 4966694 (Open Web Text)

Max Activating Token Index: 1003

Text #16

Max Range: 5.3935. Min Range: -5.3935

Max Act: 5.0259. Min Act: -0.1700

Data Index: 6067567 (Open Web Text)

Max Activating Token Index: 102

Text #17

Max Range: 5.3935. Min Range: -5.3935

Max Act: 5.0505. Min Act: -0.1700

Data Index: 814356 (Open Web Text)

Max Activating Token Index: 551

Text #18

Max Range: 5.3935. Min Range: -5.3935

Max Act: 5.0257. Min Act: -0.1700

Data Index: 147407 (Open Web Text)

Max Activating Token Index: 645

Text #19

Max Range: 5.3935. Min Range: -5.3935

Max Act: 5.0278. Min Act: -0.1700

Data Index: 3059209 (Open Web Text)

Max Activating Token Index: 106