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

Dataset: Open Web Text

Neuron 1073 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: 1.4422. Min Range: -1.4422

Max Act: 1.4422. Min Act: -0.1383

Data Index: 3173231 (Open Web Text)

Max Activating Token Index: 435

Text #1

Max Range: 1.4422. Min Range: -1.4422

Max Act: 1.4262. Min Act: -0.1699

Data Index: 5304010 (Open Web Text)

Max Activating Token Index: 400

Text #2

Max Range: 1.4422. Min Range: -1.4422

Max Act: 1.3511. Min Act: -0.1567

Data Index: 4799921 (Open Web Text)

Max Activating Token Index: 413

Text #3

Max Range: 1.4422. Min Range: -1.4422

Max Act: 1.2379. Min Act: -0.1596

Data Index: 5028479 (Open Web Text)

Max Activating Token Index: 503

Text #4

Max Range: 1.4422. Min Range: -1.4422

Max Act: 1.2205. Min Act: -0.1576

Data Index: 8315101 (Open Web Text)

Max Activating Token Index: 493

Text #5

Max Range: 1.4422. Min Range: -1.4422

Max Act: 1.1960. Min Act: -0.1580

Data Index: 8684261 (Open Web Text)

Max Activating Token Index: 429

Text #6

Max Range: 1.4422. Min Range: -1.4422

Max Act: 1.2002. Min Act: -0.1698

Data Index: 6333442 (Open Web Text)

Max Activating Token Index: 409

Text #7

Max Range: 1.4422. Min Range: -1.4422

Max Act: 1.1627. Min Act: -0.1512

Data Index: 2163461 (Open Web Text)

Max Activating Token Index: 430

Text #8

Max Range: 1.4422. Min Range: -1.4422

Max Act: 1.1660. Min Act: -0.1697

Data Index: 4799920 (Open Web Text)

Max Activating Token Index: 523

Text #9

Max Range: 1.4422. Min Range: -1.4422

Max Act: 1.1276. Min Act: -0.1480

Data Index: 5161071 (Open Web Text)

Max Activating Token Index: 1021

Text #10

Max Range: 1.4422. Min Range: -1.4422

Max Act: 1.1224. Min Act: -0.1376

Data Index: 8377034 (Open Web Text)

Max Activating Token Index: 441

Text #11

Max Range: 1.4422. Min Range: -1.4422

Max Act: 1.1236. Min Act: -0.1625

Data Index: 7616533 (Open Web Text)

Max Activating Token Index: 461

Text #12

Max Range: 1.4422. Min Range: -1.4422

Max Act: 1.1102. Min Act: -0.1533

Data Index: 8610425 (Open Web Text)

Max Activating Token Index: 1021

Text #13

Max Range: 1.4422. Min Range: -1.4422

Max Act: 1.0670. Min Act: -0.1569

Data Index: 1610857 (Open Web Text)

Max Activating Token Index: 470

Text #14

Max Range: 1.4422. Min Range: -1.4422

Max Act: 1.0695. Min Act: -0.1330

Data Index: 2814012 (Open Web Text)

Max Activating Token Index: 421

Text #15

Max Range: 1.4422. Min Range: -1.4422

Max Act: 1.1009. Min Act: -0.1652

Data Index: 3668008 (Open Web Text)

Max Activating Token Index: 519

Text #16

Max Range: 1.4422. Min Range: -1.4422

Max Act: 1.0395. Min Act: -0.1578

Data Index: 4658327 (Open Web Text)

Max Activating Token Index: 496

Text #17

Max Range: 1.4422. Min Range: -1.4422

Max Act: 1.0020. Min Act: -0.1587

Data Index: 8704137 (Open Web Text)

Max Activating Token Index: 380

Text #18

Max Range: 1.4422. Min Range: -1.4422

Max Act: 0.9813. Min Act: -0.1344

Data Index: 1505302 (Open Web Text)

Max Activating Token Index: 406

Text #19

Max Range: 1.4422. Min Range: -1.4422

Max Act: 0.9850. Min Act: -0.1690

Data Index: 5699837 (Open Web Text)

Max Activating Token Index: 992