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

Dataset: Open Web Text

Neuron 1012 in Layer 2

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: 4.2753. Min Range: -4.2753

Max Act: 4.2753. Min Act: -0.1700

Data Index: 374043 (Open Web Text)

Max Activating Token Index: 319

Text #1

Max Range: 4.2753. Min Range: -4.2753

Max Act: 4.2382. Min Act: -0.1700

Data Index: 1193824 (Open Web Text)

Max Activating Token Index: 665

Text #2

Max Range: 4.2753. Min Range: -4.2753

Max Act: 4.2091. Min Act: -0.1700

Data Index: 2494097 (Open Web Text)

Max Activating Token Index: 469

Text #3

Max Range: 4.2753. Min Range: -4.2753

Max Act: 4.2159. Min Act: -0.1700

Data Index: 1400813 (Open Web Text)

Max Activating Token Index: 277

Text #4

Max Range: 4.2753. Min Range: -4.2753

Max Act: 4.1766. Min Act: -0.1700

Data Index: 5429468 (Open Web Text)

Max Activating Token Index: 540

Text #5

Max Range: 4.2753. Min Range: -4.2753

Max Act: 4.1553. Min Act: -0.1700

Data Index: 5276944 (Open Web Text)

Max Activating Token Index: 448

Text #6

Max Range: 4.2753. Min Range: -4.2753

Max Act: 4.1434. Min Act: -0.1700

Data Index: 4846137 (Open Web Text)

Max Activating Token Index: 400

Text #7

Max Range: 4.2753. Min Range: -4.2753

Max Act: 4.1468. Min Act: -0.1700

Data Index: 8258231 (Open Web Text)

Max Activating Token Index: 499

Text #8

Max Range: 4.2753. Min Range: -4.2753

Max Act: 4.1384. Min Act: -0.1700

Data Index: 4213979 (Open Web Text)

Max Activating Token Index: 392

Text #9

Max Range: 4.2753. Min Range: -4.2753

Max Act: 4.1442. Min Act: -0.1700

Data Index: 8168714 (Open Web Text)

Max Activating Token Index: 621

Text #10

Max Range: 4.2753. Min Range: -4.2753

Max Act: 4.1544. Min Act: -0.1700

Data Index: 1004859 (Open Web Text)

Max Activating Token Index: 683

Text #11

Max Range: 4.2753. Min Range: -4.2753

Max Act: 4.1615. Min Act: -0.1700

Data Index: 7354104 (Open Web Text)

Max Activating Token Index: 530

Text #12

Max Range: 4.2753. Min Range: -4.2753

Max Act: 4.1295. Min Act: -0.1700

Data Index: 6619373 (Open Web Text)

Max Activating Token Index: 591

Text #13

Max Range: 4.2753. Min Range: -4.2753

Max Act: 4.1442. Min Act: -0.1700

Data Index: 5065665 (Open Web Text)

Max Activating Token Index: 305

Text #14

Max Range: 4.2753. Min Range: -4.2753

Max Act: 4.1115. Min Act: -0.1700

Data Index: 2449686 (Open Web Text)

Max Activating Token Index: 74

Text #15

Max Range: 4.2753. Min Range: -4.2753

Max Act: 4.1305. Min Act: -0.1700

Data Index: 1413834 (Open Web Text)

Max Activating Token Index: 953

Text #16

Max Range: 4.2753. Min Range: -4.2753

Max Act: 4.1249. Min Act: -0.1700

Data Index: 797263 (Open Web Text)

Max Activating Token Index: 409

Text #17

Max Range: 4.2753. Min Range: -4.2753

Max Act: 4.1299. Min Act: -0.1700

Data Index: 4123880 (Open Web Text)

Max Activating Token Index: 721

Text #18

Max Range: 4.2753. Min Range: -4.2753

Max Act: 4.1313. Min Act: -0.1700

Data Index: 7042608 (Open Web Text)

Max Activating Token Index: 633

Text #19

Max Range: 4.2753. Min Range: -4.2753

Max Act: 4.0831. Min Act: -0.1700

Data Index: 4914034 (Open Web Text)

Max Activating Token Index: 942