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

Dataset: Open Web Text

Neuron 2489 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: 4.7355. Min Range: -4.7355

Max Act: 4.7355. Min Act: -0.1700

Data Index: 8358819 (Open Web Text)

Max Activating Token Index: 411

Text #1

Max Range: 4.7355. Min Range: -4.7355

Max Act: 4.7139. Min Act: -0.1700

Data Index: 454407 (Open Web Text)

Max Activating Token Index: 361

Text #2

Max Range: 4.7355. Min Range: -4.7355

Max Act: 4.6623. Min Act: -0.1700

Data Index: 8728562 (Open Web Text)

Max Activating Token Index: 122

Text #3

Max Range: 4.7355. Min Range: -4.7355

Max Act: 4.5880. Min Act: -0.1700

Data Index: 6471312 (Open Web Text)

Max Activating Token Index: 207

Text #4

Max Range: 4.7355. Min Range: -4.7355

Max Act: 4.6015. Min Act: -0.1700

Data Index: 2216138 (Open Web Text)

Max Activating Token Index: 701

Text #5

Max Range: 4.7355. Min Range: -4.7355

Max Act: 4.5500. Min Act: -0.1700

Data Index: 4021204 (Open Web Text)

Max Activating Token Index: 956

Text #6

Max Range: 4.7355. Min Range: -4.7355

Max Act: 4.5697. Min Act: -0.1700

Data Index: 7772081 (Open Web Text)

Max Activating Token Index: 965

Text #7

Max Range: 4.7355. Min Range: -4.7355

Max Act: 4.5838. Min Act: -0.1700

Data Index: 7155791 (Open Web Text)

Max Activating Token Index: 691

Text #8

Max Range: 4.7355. Min Range: -4.7355

Max Act: 4.5592. Min Act: -0.1700

Data Index: 3323783 (Open Web Text)

Max Activating Token Index: 230

Text #9

Max Range: 4.7355. Min Range: -4.7355

Max Act: 4.5520. Min Act: -0.1700

Data Index: 4575225 (Open Web Text)

Max Activating Token Index: 398

Text #10

Max Range: 4.7355. Min Range: -4.7355

Max Act: 4.5149. Min Act: -0.1700

Data Index: 5800441 (Open Web Text)

Max Activating Token Index: 506

Text #11

Max Range: 4.7355. Min Range: -4.7355

Max Act: 4.5356. Min Act: -0.1700

Data Index: 8585953 (Open Web Text)

Max Activating Token Index: 231

Text #12

Max Range: 4.7355. Min Range: -4.7355

Max Act: 4.5484. Min Act: -0.1700

Data Index: 6819196 (Open Web Text)

Max Activating Token Index: 1009

Text #13

Max Range: 4.7355. Min Range: -4.7355

Max Act: 4.5410. Min Act: -0.1700

Data Index: 7665493 (Open Web Text)

Max Activating Token Index: 322

Text #14

Max Range: 4.7355. Min Range: -4.7355

Max Act: 4.5071. Min Act: -0.1700

Data Index: 4236387 (Open Web Text)

Max Activating Token Index: 670

Text #15

Max Range: 4.7355. Min Range: -4.7355

Max Act: 4.5231. Min Act: -0.1700

Data Index: 2893196 (Open Web Text)

Max Activating Token Index: 38

Text #16

Max Range: 4.7355. Min Range: -4.7355

Max Act: 4.4989. Min Act: -0.1700

Data Index: 2864025 (Open Web Text)

Max Activating Token Index: 897

Text #17

Max Range: 4.7355. Min Range: -4.7355

Max Act: 4.4718. Min Act: -0.1700

Data Index: 2023692 (Open Web Text)

Max Activating Token Index: 616

Text #18

Max Range: 4.7355. Min Range: -4.7355

Max Act: 4.5279. Min Act: -0.1700

Data Index: 2019799 (Open Web Text)

Max Activating Token Index: 557

Text #19

Max Range: 4.7355. Min Range: -4.7355

Max Act: 4.4666. Min Act: -0.1700

Data Index: 437491 (Open Web Text)

Max Activating Token Index: 576