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

Dataset: Open Web Text

Neuron 2075 in Layer 4

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: 5.6485. Min Range: -5.6485

Max Act: 5.6485. Min Act: -0.1700

Data Index: 3764407 (Open Web Text)

Max Activating Token Index: 778

Text #1

Max Range: 5.6485. Min Range: -5.6485

Max Act: 5.4421. Min Act: -0.1700

Data Index: 6782213 (Open Web Text)

Max Activating Token Index: 972

Text #2

Max Range: 5.6485. Min Range: -5.6485

Max Act: 5.4483. Min Act: -0.1700

Data Index: 1197714 (Open Web Text)

Max Activating Token Index: 911

Text #3

Max Range: 5.6485. Min Range: -5.6485

Max Act: 5.4324. Min Act: -0.1700

Data Index: 8656567 (Open Web Text)

Max Activating Token Index: 133

Text #4

Max Range: 5.6485. Min Range: -5.6485

Max Act: 5.3984. Min Act: -0.1700

Data Index: 3888407 (Open Web Text)

Max Activating Token Index: 314

Text #5

Max Range: 5.6485. Min Range: -5.6485

Max Act: 5.3927. Min Act: -0.1700

Data Index: 5178240 (Open Web Text)

Max Activating Token Index: 369

Text #6

Max Range: 5.6485. Min Range: -5.6485

Max Act: 5.3717. Min Act: -0.1700

Data Index: 312973 (Open Web Text)

Max Activating Token Index: 607

Text #7

Max Range: 5.6485. Min Range: -5.6485

Max Act: 5.3909. Min Act: -0.1700

Data Index: 4822241 (Open Web Text)

Max Activating Token Index: 512

Text #8

Max Range: 5.6485. Min Range: -5.6485

Max Act: 5.3124. Min Act: -0.1700

Data Index: 6155732 (Open Web Text)

Max Activating Token Index: 479

Text #9

Max Range: 5.6485. Min Range: -5.6485

Max Act: 5.2686. Min Act: -0.1700

Data Index: 4533634 (Open Web Text)

Max Activating Token Index: 931

Text #10

Max Range: 5.6485. Min Range: -5.6485

Max Act: 5.2579. Min Act: -0.1700

Data Index: 1384772 (Open Web Text)

Max Activating Token Index: 170

Text #11

Max Range: 5.6485. Min Range: -5.6485

Max Act: 5.2465. Min Act: -0.1700

Data Index: 5716052 (Open Web Text)

Max Activating Token Index: 305

Text #12

Max Range: 5.6485. Min Range: -5.6485

Max Act: 5.2056. Min Act: -0.1700

Data Index: 2179191 (Open Web Text)

Max Activating Token Index: 906

Text #13

Max Range: 5.6485. Min Range: -5.6485

Max Act: 5.1889. Min Act: -0.1700

Data Index: 158193 (Open Web Text)

Max Activating Token Index: 258

Text #14

Max Range: 5.6485. Min Range: -5.6485

Max Act: 5.1669. Min Act: -0.1700

Data Index: 525790 (Open Web Text)

Max Activating Token Index: 266

Text #15

Max Range: 5.6485. Min Range: -5.6485

Max Act: 5.1812. Min Act: -0.1700

Data Index: 7179038 (Open Web Text)

Max Activating Token Index: 914

Text #16

Max Range: 5.6485. Min Range: -5.6485

Max Act: 5.1654. Min Act: -0.1700

Data Index: 259075 (Open Web Text)

Max Activating Token Index: 661

Text #17

Max Range: 5.6485. Min Range: -5.6485

Max Act: 5.1378. Min Act: -0.1700

Data Index: 1124983 (Open Web Text)

Max Activating Token Index: 54

Text #18

Max Range: 5.6485. Min Range: -5.6485

Max Act: 5.1295. Min Act: -0.1700

Data Index: 4065302 (Open Web Text)

Max Activating Token Index: 509

Text #19

Max Range: 5.6485. Min Range: -5.6485

Max Act: 5.0841. Min Act: -0.1700

Data Index: 5406233 (Open Web Text)

Max Activating Token Index: 1001