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

Dataset: Open Web Text

Neuron 2675 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: 4.9321. Min Range: -4.9321

Max Act: 4.9321. Min Act: -0.1700

Data Index: 7382485 (Open Web Text)

Max Activating Token Index: 93

Text #1

Max Range: 4.9321. Min Range: -4.9321

Max Act: 4.8975. Min Act: -0.1700

Data Index: 6108051 (Open Web Text)

Max Activating Token Index: 646

Text #2

Max Range: 4.9321. Min Range: -4.9321

Max Act: 4.9148. Min Act: -0.1700

Data Index: 1467616 (Open Web Text)

Max Activating Token Index: 592

Text #3

Max Range: 4.9321. Min Range: -4.9321

Max Act: 4.8715. Min Act: -0.1700

Data Index: 4201203 (Open Web Text)

Max Activating Token Index: 706

Text #4

Max Range: 4.9321. Min Range: -4.9321

Max Act: 4.8437. Min Act: -0.1700

Data Index: 5973486 (Open Web Text)

Max Activating Token Index: 920

Text #5

Max Range: 4.9321. Min Range: -4.9321

Max Act: 4.8491. Min Act: -0.1700

Data Index: 6282728 (Open Web Text)

Max Activating Token Index: 180

Text #6

Max Range: 4.9321. Min Range: -4.9321

Max Act: 4.8178. Min Act: -0.1700

Data Index: 1869034 (Open Web Text)

Max Activating Token Index: 837

Text #7

Max Range: 4.9321. Min Range: -4.9321

Max Act: 4.7792. Min Act: -0.1700

Data Index: 7239107 (Open Web Text)

Max Activating Token Index: 390

Text #8

Max Range: 4.9321. Min Range: -4.9321

Max Act: 4.7375. Min Act: -0.1700

Data Index: 1280862 (Open Web Text)

Max Activating Token Index: 998

Text #9

Max Range: 4.9321. Min Range: -4.9321

Max Act: 4.7637. Min Act: -0.1700

Data Index: 3110000 (Open Web Text)

Max Activating Token Index: 329

Text #10

Max Range: 4.9321. Min Range: -4.9321

Max Act: 4.7648. Min Act: -0.1700

Data Index: 8051503 (Open Web Text)

Max Activating Token Index: 644

Text #11

Max Range: 4.9321. Min Range: -4.9321

Max Act: 4.7389. Min Act: -0.1700

Data Index: 7047428 (Open Web Text)

Max Activating Token Index: 1011

Text #12

Max Range: 4.9321. Min Range: -4.9321

Max Act: 4.7009. Min Act: -0.1700

Data Index: 4700839 (Open Web Text)

Max Activating Token Index: 773

Text #13

Max Range: 4.9321. Min Range: -4.9321

Max Act: 4.7558. Min Act: -0.1700

Data Index: 6669386 (Open Web Text)

Max Activating Token Index: 648

Text #14

Max Range: 4.9321. Min Range: -4.9321

Max Act: 4.7280. Min Act: -0.1700

Data Index: 2092642 (Open Web Text)

Max Activating Token Index: 464

Text #15

Max Range: 4.9321. Min Range: -4.9321

Max Act: 4.7692. Min Act: -0.1700

Data Index: 8195789 (Open Web Text)

Max Activating Token Index: 713

Text #16

Max Range: 4.9321. Min Range: -4.9321

Max Act: 4.6961. Min Act: -0.1700

Data Index: 3879491 (Open Web Text)

Max Activating Token Index: 185

Text #17

Max Range: 4.9321. Min Range: -4.9321

Max Act: 4.7183. Min Act: -0.1700

Data Index: 3273873 (Open Web Text)

Max Activating Token Index: 26

Text #18

Max Range: 4.9321. Min Range: -4.9321

Max Act: 4.7189. Min Act: -0.1700

Data Index: 1347464 (Open Web Text)

Max Activating Token Index: 690

Text #19

Max Range: 4.9321. Min Range: -4.9321

Max Act: 4.7449. Min Act: -0.1700

Data Index: 2164320 (Open Web Text)

Max Activating Token Index: 30