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

Dataset: Open Web Text

Neuron 625 in Layer 1

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: 5.0973. Min Range: -5.0973

Max Act: 5.0973. Min Act: -0.1700

Data Index: 2775809 (Open Web Text)

Max Activating Token Index: 143

Text #1

Max Range: 5.0973. Min Range: -5.0973

Max Act: 5.0424. Min Act: -0.1700

Data Index: 7331446 (Open Web Text)

Max Activating Token Index: 404

Text #2

Max Range: 5.0973. Min Range: -5.0973

Max Act: 4.9020. Min Act: -0.1700

Data Index: 681331 (Open Web Text)

Max Activating Token Index: 233

Text #3

Max Range: 5.0973. Min Range: -5.0973

Max Act: 4.8852. Min Act: -0.1700

Data Index: 7135072 (Open Web Text)

Max Activating Token Index: 54

Text #4

Max Range: 5.0973. Min Range: -5.0973

Max Act: 4.9050. Min Act: -0.1700

Data Index: 1074228 (Open Web Text)

Max Activating Token Index: 307

Text #5

Max Range: 5.0973. Min Range: -5.0973

Max Act: 4.8576. Min Act: -0.1700

Data Index: 8454482 (Open Web Text)

Max Activating Token Index: 290

Text #6

Max Range: 5.0973. Min Range: -5.0973

Max Act: 4.8624. Min Act: -0.1700

Data Index: 636197 (Open Web Text)

Max Activating Token Index: 37

Text #7

Max Range: 5.0973. Min Range: -5.0973

Max Act: 4.8766. Min Act: -0.1700

Data Index: 4441022 (Open Web Text)

Max Activating Token Index: 258

Text #8

Max Range: 5.0973. Min Range: -5.0973

Max Act: 4.8055. Min Act: -0.1700

Data Index: 2870388 (Open Web Text)

Max Activating Token Index: 246

Text #9

Max Range: 5.0973. Min Range: -5.0973

Max Act: 4.8341. Min Act: -0.1700

Data Index: 7399026 (Open Web Text)

Max Activating Token Index: 510

Text #10

Max Range: 5.0973. Min Range: -5.0973

Max Act: 4.8348. Min Act: -0.1700

Data Index: 2428952 (Open Web Text)

Max Activating Token Index: 188

Text #11

Max Range: 5.0973. Min Range: -5.0973

Max Act: 4.8282. Min Act: -0.1700

Data Index: 7244914 (Open Web Text)

Max Activating Token Index: 234

Text #12

Max Range: 5.0973. Min Range: -5.0973

Max Act: 4.7745. Min Act: -0.1700

Data Index: 7185425 (Open Web Text)

Max Activating Token Index: 27

Text #13

Max Range: 5.0973. Min Range: -5.0973

Max Act: 4.8063. Min Act: -0.1700

Data Index: 7567651 (Open Web Text)

Max Activating Token Index: 358

Text #14

Max Range: 5.0973. Min Range: -5.0973

Max Act: 4.7963. Min Act: -0.1700

Data Index: 5758283 (Open Web Text)

Max Activating Token Index: 103

Text #15

Max Range: 5.0973. Min Range: -5.0973

Max Act: 4.8012. Min Act: -0.1700

Data Index: 4141882 (Open Web Text)

Max Activating Token Index: 604

Text #16

Max Range: 5.0973. Min Range: -5.0973

Max Act: 4.7966. Min Act: -0.1700

Data Index: 6981915 (Open Web Text)

Max Activating Token Index: 79

Text #17

Max Range: 5.0973. Min Range: -5.0973

Max Act: 4.8131. Min Act: -0.1700

Data Index: 76934 (Open Web Text)

Max Activating Token Index: 651

Text #18

Max Range: 5.0973. Min Range: -5.0973

Max Act: 4.7886. Min Act: -0.1700

Data Index: 6455063 (Open Web Text)

Max Activating Token Index: 334

Text #19

Max Range: 5.0973. Min Range: -5.0973

Max Act: 4.8212. Min Act: -0.1700

Data Index: 3944172 (Open Web Text)

Max Activating Token Index: 127