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

Dataset: Open Web Text

Neuron 712 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: 1.5899. Min Range: -1.5899

Max Act: 1.5899. Min Act: -0.1694

Data Index: 4449996 (Open Web Text)

Max Activating Token Index: 376

Text #1

Max Range: 1.5899. Min Range: -1.5899

Max Act: 1.5847. Min Act: -0.1696

Data Index: 7165714 (Open Web Text)

Max Activating Token Index: 422

Text #2

Max Range: 1.5899. Min Range: -1.5899

Max Act: 1.5693. Min Act: -0.1700

Data Index: 8199494 (Open Web Text)

Max Activating Token Index: 685

Text #3

Max Range: 1.5899. Min Range: -1.5899

Max Act: 1.5603. Min Act: -0.1700

Data Index: 5867030 (Open Web Text)

Max Activating Token Index: 378

Text #4

Max Range: 1.5899. Min Range: -1.5899

Max Act: 1.5563. Min Act: -0.1700

Data Index: 5525577 (Open Web Text)

Max Activating Token Index: 154

Text #5

Max Range: 1.5899. Min Range: -1.5899

Max Act: 1.5553. Min Act: -0.1700

Data Index: 5611605 (Open Web Text)

Max Activating Token Index: 128

Text #6

Max Range: 1.5899. Min Range: -1.5899

Max Act: 1.5559. Min Act: -0.1700

Data Index: 4685266 (Open Web Text)

Max Activating Token Index: 392

Text #7

Max Range: 1.5899. Min Range: -1.5899

Max Act: 1.5482. Min Act: -0.1700

Data Index: 2031263 (Open Web Text)

Max Activating Token Index: 684

Text #8

Max Range: 1.5899. Min Range: -1.5899

Max Act: 1.5341. Min Act: -0.1700

Data Index: 389337 (Open Web Text)

Max Activating Token Index: 729

Text #9

Max Range: 1.5899. Min Range: -1.5899

Max Act: 1.5344. Min Act: -0.1589

Data Index: 5837136 (Open Web Text)

Max Activating Token Index: 501

Text #10

Max Range: 1.5899. Min Range: -1.5899

Max Act: 1.5349. Min Act: -0.1700

Data Index: 5304552 (Open Web Text)

Max Activating Token Index: 650

Text #11

Max Range: 1.5899. Min Range: -1.5899

Max Act: 1.5342. Min Act: -0.1696

Data Index: 7748159 (Open Web Text)

Max Activating Token Index: 690

Text #12

Max Range: 1.5899. Min Range: -1.5899

Max Act: 1.5252. Min Act: -0.1700

Data Index: 690930 (Open Web Text)

Max Activating Token Index: 497

Text #13

Max Range: 1.5899. Min Range: -1.5899

Max Act: 1.5224. Min Act: -0.1700

Data Index: 7414114 (Open Web Text)

Max Activating Token Index: 558

Text #14

Max Range: 1.5899. Min Range: -1.5899

Max Act: 1.5060. Min Act: -0.1699

Data Index: 7889844 (Open Web Text)

Max Activating Token Index: 342

Text #15

Max Range: 1.5899. Min Range: -1.5899

Max Act: 1.5056. Min Act: -0.1700

Data Index: 8082920 (Open Web Text)

Max Activating Token Index: 796

Text #16

Max Range: 1.5899. Min Range: -1.5899

Max Act: 1.5065. Min Act: -0.1699

Data Index: 8607451 (Open Web Text)

Max Activating Token Index: 353

Text #17

Max Range: 1.5899. Min Range: -1.5899

Max Act: 1.4966. Min Act: -0.1700

Data Index: 1564208 (Open Web Text)

Max Activating Token Index: 593

Text #18

Max Range: 1.5899. Min Range: -1.5899

Max Act: 1.4864. Min Act: -0.1700

Data Index: 684875 (Open Web Text)

Max Activating Token Index: 1001

Text #19

Max Range: 1.5899. Min Range: -1.5899

Max Act: 1.4923. Min Act: -0.1700

Data Index: 2171006 (Open Web Text)

Max Activating Token Index: 940