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

Dataset: Open Web Text

Neuron 2041 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: 3.5354. Min Range: -3.5354

Max Act: 3.5354. Min Act: -0.1700

Data Index: 4004430 (Open Web Text)

Max Activating Token Index: 266

Text #1

Max Range: 3.5354. Min Range: -3.5354

Max Act: 3.5286. Min Act: -0.1700

Data Index: 633552 (Open Web Text)

Max Activating Token Index: 393

Text #2

Max Range: 3.5354. Min Range: -3.5354

Max Act: 3.4413. Min Act: -0.1700

Data Index: 7804140 (Open Web Text)

Max Activating Token Index: 640

Text #3

Max Range: 3.5354. Min Range: -3.5354

Max Act: 3.3322. Min Act: -0.1700

Data Index: 510239 (Open Web Text)

Max Activating Token Index: 1022

Text #4

Max Range: 3.5354. Min Range: -3.5354

Max Act: 3.2952. Min Act: -0.1700

Data Index: 175839 (Open Web Text)

Max Activating Token Index: 609

Text #5

Max Range: 3.5354. Min Range: -3.5354

Max Act: 3.2733. Min Act: -0.1700

Data Index: 4802257 (Open Web Text)

Max Activating Token Index: 516

Text #6

Max Range: 3.5354. Min Range: -3.5354

Max Act: 3.3072. Min Act: -0.1700

Data Index: 2106945 (Open Web Text)

Max Activating Token Index: 886

Text #7

Max Range: 3.5354. Min Range: -3.5354

Max Act: 3.2739. Min Act: -0.1700

Data Index: 4118537 (Open Web Text)

Max Activating Token Index: 908

Text #8

Max Range: 3.5354. Min Range: -3.5354

Max Act: 3.2210. Min Act: -0.1700

Data Index: 8173998 (Open Web Text)

Max Activating Token Index: 389

Text #9

Max Range: 3.5354. Min Range: -3.5354

Max Act: 3.2119. Min Act: -0.1700

Data Index: 3915577 (Open Web Text)

Max Activating Token Index: 512

Text #10

Max Range: 3.5354. Min Range: -3.5354

Max Act: 3.2463. Min Act: -0.1700

Data Index: 5425257 (Open Web Text)

Max Activating Token Index: 422

Text #11

Max Range: 3.5354. Min Range: -3.5354

Max Act: 3.1962. Min Act: -0.1700

Data Index: 6510492 (Open Web Text)

Max Activating Token Index: 612

Text #12

Max Range: 3.5354. Min Range: -3.5354

Max Act: 3.1859. Min Act: -0.1700

Data Index: 8006462 (Open Web Text)

Max Activating Token Index: 194

Text #13

Max Range: 3.5354. Min Range: -3.5354

Max Act: 3.1631. Min Act: -0.1700

Data Index: 277022 (Open Web Text)

Max Activating Token Index: 305

Text #14

Max Range: 3.5354. Min Range: -3.5354

Max Act: 3.1862. Min Act: -0.1700

Data Index: 6218524 (Open Web Text)

Max Activating Token Index: 385

Text #15

Max Range: 3.5354. Min Range: -3.5354

Max Act: 3.1885. Min Act: -0.1700

Data Index: 243075 (Open Web Text)

Max Activating Token Index: 605

Text #16

Max Range: 3.5354. Min Range: -3.5354

Max Act: 3.1974. Min Act: -0.1700

Data Index: 7871818 (Open Web Text)

Max Activating Token Index: 51

Text #17

Max Range: 3.5354. Min Range: -3.5354

Max Act: 3.1886. Min Act: -0.1700

Data Index: 3367256 (Open Web Text)

Max Activating Token Index: 758

Text #18

Max Range: 3.5354. Min Range: -3.5354

Max Act: 3.1891. Min Act: -0.1700

Data Index: 5651096 (Open Web Text)

Max Activating Token Index: 864

Text #19

Max Range: 3.5354. Min Range: -3.5354

Max Act: 3.1628. Min Act: -0.1700

Data Index: 6927261 (Open Web Text)

Max Activating Token Index: 959