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

Dataset: Open Web Text

Neuron 229 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: 5.0994. Min Range: -5.0994

Max Act: 5.0994. Min Act: -0.1700

Data Index: 5706918 (Open Web Text)

Max Activating Token Index: 324

Text #1

Max Range: 5.0994. Min Range: -5.0994

Max Act: 5.0856. Min Act: -0.1700

Data Index: 5624619 (Open Web Text)

Max Activating Token Index: 447

Text #2

Max Range: 5.0994. Min Range: -5.0994

Max Act: 5.0158. Min Act: -0.1700

Data Index: 7971039 (Open Web Text)

Max Activating Token Index: 568

Text #3

Max Range: 5.0994. Min Range: -5.0994

Max Act: 5.0108. Min Act: -0.1700

Data Index: 6084549 (Open Web Text)

Max Activating Token Index: 367

Text #4

Max Range: 5.0994. Min Range: -5.0994

Max Act: 4.9969. Min Act: -0.1700

Data Index: 8125014 (Open Web Text)

Max Activating Token Index: 740

Text #5

Max Range: 5.0994. Min Range: -5.0994

Max Act: 5.0083. Min Act: -0.1700

Data Index: 2549690 (Open Web Text)

Max Activating Token Index: 463

Text #6

Max Range: 5.0994. Min Range: -5.0994

Max Act: 4.9250. Min Act: -0.1700

Data Index: 505237 (Open Web Text)

Max Activating Token Index: 538

Text #7

Max Range: 5.0994. Min Range: -5.0994

Max Act: 4.9529. Min Act: -0.1700

Data Index: 1891140 (Open Web Text)

Max Activating Token Index: 590

Text #8

Max Range: 5.0994. Min Range: -5.0994

Max Act: 4.9618. Min Act: -0.1700

Data Index: 2453951 (Open Web Text)

Max Activating Token Index: 359

Text #9

Max Range: 5.0994. Min Range: -5.0994

Max Act: 4.9321. Min Act: -0.1695

Data Index: 5146611 (Open Web Text)

Max Activating Token Index: 841

Text #10

Max Range: 5.0994. Min Range: -5.0994

Max Act: 5.0557. Min Act: -0.1700

Data Index: 8619137 (Open Web Text)

Max Activating Token Index: 570

Text #11

Max Range: 5.0994. Min Range: -5.0994

Max Act: 4.9624. Min Act: -0.1700

Data Index: 2170307 (Open Web Text)

Max Activating Token Index: 328

Text #12

Max Range: 5.0994. Min Range: -5.0994

Max Act: 4.9475. Min Act: -0.1700

Data Index: 7318214 (Open Web Text)

Max Activating Token Index: 780

Text #13

Max Range: 5.0994. Min Range: -5.0994

Max Act: 4.8570. Min Act: -0.1700

Data Index: 3225497 (Open Web Text)

Max Activating Token Index: 171

Text #14

Max Range: 5.0994. Min Range: -5.0994

Max Act: 4.9034. Min Act: -0.1700

Data Index: 5078849 (Open Web Text)

Max Activating Token Index: 305

Text #15

Max Range: 5.0994. Min Range: -5.0994

Max Act: 4.8650. Min Act: -0.1700

Data Index: 6477915 (Open Web Text)

Max Activating Token Index: 400

Text #16

Max Range: 5.0994. Min Range: -5.0994

Max Act: 4.7978. Min Act: -0.1700

Data Index: 7447226 (Open Web Text)

Max Activating Token Index: 349

Text #17

Max Range: 5.0994. Min Range: -5.0994

Max Act: 4.8037. Min Act: -0.1698

Data Index: 2494759 (Open Web Text)

Max Activating Token Index: 32

Text #18

Max Range: 5.0994. Min Range: -5.0994

Max Act: 4.8542. Min Act: -0.1700

Data Index: 5078850 (Open Web Text)

Max Activating Token Index: 330

Text #19

Max Range: 5.0994. Min Range: -5.0994

Max Act: 4.8202. Min Act: -0.1698

Data Index: 695852 (Open Web Text)

Max Activating Token Index: 509