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

Dataset: Open Web Text

Neuron 908 in Layer 3

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: 4.2327. Min Range: -4.2327

Max Act: 4.2327. Min Act: -0.1700

Data Index: 432569 (Open Web Text)

Max Activating Token Index: 566

Text #1

Max Range: 4.2327. Min Range: -4.2327

Max Act: 4.2286. Min Act: -0.1700

Data Index: 7476696 (Open Web Text)

Max Activating Token Index: 834

Text #2

Max Range: 4.2327. Min Range: -4.2327

Max Act: 4.1879. Min Act: -0.1700

Data Index: 997003 (Open Web Text)

Max Activating Token Index: 857

Text #3

Max Range: 4.2327. Min Range: -4.2327

Max Act: 4.1681. Min Act: -0.1700

Data Index: 5942167 (Open Web Text)

Max Activating Token Index: 111

Text #4

Max Range: 4.2327. Min Range: -4.2327

Max Act: 4.1482. Min Act: -0.1700

Data Index: 7071723 (Open Web Text)

Max Activating Token Index: 506

Text #5

Max Range: 4.2327. Min Range: -4.2327

Max Act: 4.1276. Min Act: -0.1700

Data Index: 6871813 (Open Web Text)

Max Activating Token Index: 148

Text #6

Max Range: 4.2327. Min Range: -4.2327

Max Act: 4.1116. Min Act: -0.1700

Data Index: 403485 (Open Web Text)

Max Activating Token Index: 279

Text #7

Max Range: 4.2327. Min Range: -4.2327

Max Act: 4.0909. Min Act: -0.1700

Data Index: 3051865 (Open Web Text)

Max Activating Token Index: 612

Text #8

Max Range: 4.2327. Min Range: -4.2327

Max Act: 4.1120. Min Act: -0.1700

Data Index: 7385308 (Open Web Text)

Max Activating Token Index: 830

Text #9

Max Range: 4.2327. Min Range: -4.2327

Max Act: 4.0714. Min Act: -0.1700

Data Index: 345507 (Open Web Text)

Max Activating Token Index: 1004

Text #10

Max Range: 4.2327. Min Range: -4.2327

Max Act: 4.0792. Min Act: -0.1700

Data Index: 1802388 (Open Web Text)

Max Activating Token Index: 337

Text #11

Max Range: 4.2327. Min Range: -4.2327

Max Act: 4.0782. Min Act: -0.1700

Data Index: 5275028 (Open Web Text)

Max Activating Token Index: 303

Text #12

Max Range: 4.2327. Min Range: -4.2327

Max Act: 4.0532. Min Act: -0.1700

Data Index: 373106 (Open Web Text)

Max Activating Token Index: 549

Text #13

Max Range: 4.2327. Min Range: -4.2327

Max Act: 4.0591. Min Act: -0.1700

Data Index: 7523440 (Open Web Text)

Max Activating Token Index: 320

Text #14

Max Range: 4.2327. Min Range: -4.2327

Max Act: 4.0450. Min Act: -0.1700

Data Index: 1681851 (Open Web Text)

Max Activating Token Index: 787

Text #15

Max Range: 4.2327. Min Range: -4.2327

Max Act: 4.0825. Min Act: -0.1700

Data Index: 1471236 (Open Web Text)

Max Activating Token Index: 435

Text #16

Max Range: 4.2327. Min Range: -4.2327

Max Act: 4.0764. Min Act: -0.1700

Data Index: 5830234 (Open Web Text)

Max Activating Token Index: 560

Text #17

Max Range: 4.2327. Min Range: -4.2327

Max Act: 4.0411. Min Act: -0.1700

Data Index: 927045 (Open Web Text)

Max Activating Token Index: 719

Text #18

Max Range: 4.2327. Min Range: -4.2327

Max Act: 4.0050. Min Act: -0.1700

Data Index: 425660 (Open Web Text)

Max Activating Token Index: 793

Text #19

Max Range: 4.2327. Min Range: -4.2327

Max Act: 4.0542. Min Act: -0.1700

Data Index: 7040603 (Open Web Text)

Max Activating Token Index: 124