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

Dataset: Open Web Text

Neuron 2043 in Layer 3

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: 3.8994. Min Range: -3.8994

Max Act: 3.8994. Min Act: -0.1700

Data Index: 3325206 (Open Web Text)

Max Activating Token Index: 540

Text #1

Max Range: 3.8994. Min Range: -3.8994

Max Act: 3.8387. Min Act: -0.1700

Data Index: 1359751 (Open Web Text)

Max Activating Token Index: 543

Text #2

Max Range: 3.8994. Min Range: -3.8994

Max Act: 3.8253. Min Act: -0.1700

Data Index: 3537883 (Open Web Text)

Max Activating Token Index: 1017

Text #3

Max Range: 3.8994. Min Range: -3.8994

Max Act: 3.7852. Min Act: -0.1700

Data Index: 2646540 (Open Web Text)

Max Activating Token Index: 573

Text #4

Max Range: 3.8994. Min Range: -3.8994

Max Act: 3.7991. Min Act: -0.1700

Data Index: 3268234 (Open Web Text)

Max Activating Token Index: 390

Text #5

Max Range: 3.8994. Min Range: -3.8994

Max Act: 3.7385. Min Act: -0.1700

Data Index: 6418911 (Open Web Text)

Max Activating Token Index: 534

Text #6

Max Range: 3.8994. Min Range: -3.8994

Max Act: 3.6564. Min Act: -0.1700

Data Index: 1391425 (Open Web Text)

Max Activating Token Index: 583

Text #7

Max Range: 3.8994. Min Range: -3.8994

Max Act: 3.6576. Min Act: -0.1700

Data Index: 2858528 (Open Web Text)

Max Activating Token Index: 553

Text #8

Max Range: 3.8994. Min Range: -3.8994

Max Act: 3.6395. Min Act: -0.1700

Data Index: 92449 (Open Web Text)

Max Activating Token Index: 77

Text #9

Max Range: 3.8994. Min Range: -3.8994

Max Act: 3.6596. Min Act: -0.1700

Data Index: 112115 (Open Web Text)

Max Activating Token Index: 164

Text #10

Max Range: 3.8994. Min Range: -3.8994

Max Act: 3.6311. Min Act: -0.1700

Data Index: 5857244 (Open Web Text)

Max Activating Token Index: 470

Text #11

Max Range: 3.8994. Min Range: -3.8994

Max Act: 3.5466. Min Act: -0.1700

Data Index: 5310783 (Open Web Text)

Max Activating Token Index: 226

Text #12

Max Range: 3.8994. Min Range: -3.8994

Max Act: 3.6041. Min Act: -0.1700

Data Index: 2649372 (Open Web Text)

Max Activating Token Index: 950

Text #13

Max Range: 3.8994. Min Range: -3.8994

Max Act: 3.5797. Min Act: -0.1700

Data Index: 6414358 (Open Web Text)

Max Activating Token Index: 80

Text #14

Max Range: 3.8994. Min Range: -3.8994

Max Act: 3.5612. Min Act: -0.1700

Data Index: 1950784 (Open Web Text)

Max Activating Token Index: 686

Text #15

Max Range: 3.8994. Min Range: -3.8994

Max Act: 3.5280. Min Act: -0.1700

Data Index: 4839775 (Open Web Text)

Max Activating Token Index: 196

Text #16

Max Range: 3.8994. Min Range: -3.8994

Max Act: 3.5295. Min Act: -0.1700

Data Index: 6481267 (Open Web Text)

Max Activating Token Index: 94

Text #17

Max Range: 3.8994. Min Range: -3.8994

Max Act: 3.5637. Min Act: -0.1700

Data Index: 3034264 (Open Web Text)

Max Activating Token Index: 840

Text #18

Max Range: 3.8994. Min Range: -3.8994

Max Act: 3.5582. Min Act: -0.1700

Data Index: 7067804 (Open Web Text)

Max Activating Token Index: 404

Text #19

Max Range: 3.8994. Min Range: -3.8994

Max Act: 3.5551. Min Act: -0.1700

Data Index: 6027812 (Open Web Text)

Max Activating Token Index: 845