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

Dataset: Open Web Text

Neuron 2404 in Layer 5

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: 3.9092. Min Range: -3.9092

Max Act: 3.9092. Min Act: -0.1700

Data Index: 3069343 (Open Web Text)

Max Activating Token Index: 468

Text #1

Max Range: 3.9092. Min Range: -3.9092

Max Act: 3.8300. Min Act: -0.1700

Data Index: 384303 (Open Web Text)

Max Activating Token Index: 842

Text #2

Max Range: 3.9092. Min Range: -3.9092

Max Act: 3.8280. Min Act: -0.1700

Data Index: 273266 (Open Web Text)

Max Activating Token Index: 938

Text #3

Max Range: 3.9092. Min Range: -3.9092

Max Act: 3.7544. Min Act: -0.1700

Data Index: 286760 (Open Web Text)

Max Activating Token Index: 968

Text #4

Max Range: 3.9092. Min Range: -3.9092

Max Act: 3.7966. Min Act: -0.1700

Data Index: 6844150 (Open Web Text)

Max Activating Token Index: 726

Text #5

Max Range: 3.9092. Min Range: -3.9092

Max Act: 3.8029. Min Act: -0.1700

Data Index: 5482066 (Open Web Text)

Max Activating Token Index: 691

Text #6

Max Range: 3.9092. Min Range: -3.9092

Max Act: 3.7654. Min Act: -0.1700

Data Index: 960279 (Open Web Text)

Max Activating Token Index: 793

Text #7

Max Range: 3.9092. Min Range: -3.9092

Max Act: 3.7819. Min Act: -0.1700

Data Index: 2283340 (Open Web Text)

Max Activating Token Index: 463

Text #8

Max Range: 3.9092. Min Range: -3.9092

Max Act: 3.7382. Min Act: -0.1700

Data Index: 3439937 (Open Web Text)

Max Activating Token Index: 930

Text #9

Max Range: 3.9092. Min Range: -3.9092

Max Act: 3.7388. Min Act: -0.1700

Data Index: 2484009 (Open Web Text)

Max Activating Token Index: 566

Text #10

Max Range: 3.9092. Min Range: -3.9092

Max Act: 3.7508. Min Act: -0.1700

Data Index: 8460752 (Open Web Text)

Max Activating Token Index: 578

Text #11

Max Range: 3.9092. Min Range: -3.9092

Max Act: 3.7363. Min Act: -0.1700

Data Index: 4745996 (Open Web Text)

Max Activating Token Index: 84

Text #12

Max Range: 3.9092. Min Range: -3.9092

Max Act: 3.7436. Min Act: -0.1700

Data Index: 6844882 (Open Web Text)

Max Activating Token Index: 43

Text #13

Max Range: 3.9092. Min Range: -3.9092

Max Act: 3.7647. Min Act: -0.1700

Data Index: 2604073 (Open Web Text)

Max Activating Token Index: 928

Text #14

Max Range: 3.9092. Min Range: -3.9092

Max Act: 3.7286. Min Act: -0.1700

Data Index: 1988992 (Open Web Text)

Max Activating Token Index: 350

Text #15

Max Range: 3.9092. Min Range: -3.9092

Max Act: 3.6836. Min Act: -0.1700

Data Index: 6047505 (Open Web Text)

Max Activating Token Index: 971

Text #16

Max Range: 3.9092. Min Range: -3.9092

Max Act: 3.6883. Min Act: -0.1700

Data Index: 3716266 (Open Web Text)

Max Activating Token Index: 485

Text #17

Max Range: 3.9092. Min Range: -3.9092

Max Act: 3.7000. Min Act: -0.1700

Data Index: 4151012 (Open Web Text)

Max Activating Token Index: 191

Text #18

Max Range: 3.9092. Min Range: -3.9092

Max Act: 3.7151. Min Act: -0.1700

Data Index: 4151013 (Open Web Text)

Max Activating Token Index: 563

Text #19

Max Range: 3.9092. Min Range: -3.9092

Max Act: 3.6259. Min Act: -0.1700

Data Index: 6536604 (Open Web Text)

Max Activating Token Index: 713