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

Dataset: Open Web Text

Neuron 1741 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: 6.0296. Min Range: -6.0296

Max Act: 6.0296. Min Act: -0.1700

Data Index: 8816557 (Open Web Text)

Max Activating Token Index: 664

Text #1

Max Range: 6.0296. Min Range: -6.0296

Max Act: 6.0206. Min Act: -0.1700

Data Index: 2708897 (Open Web Text)

Max Activating Token Index: 690

Text #2

Max Range: 6.0296. Min Range: -6.0296

Max Act: 5.7779. Min Act: -0.1700

Data Index: 4644808 (Open Web Text)

Max Activating Token Index: 899

Text #3

Max Range: 6.0296. Min Range: -6.0296

Max Act: 5.7747. Min Act: -0.1700

Data Index: 1931757 (Open Web Text)

Max Activating Token Index: 624

Text #4

Max Range: 6.0296. Min Range: -6.0296

Max Act: 5.6675. Min Act: -0.1700

Data Index: 2814572 (Open Web Text)

Max Activating Token Index: 819

Text #5

Max Range: 6.0296. Min Range: -6.0296

Max Act: 5.6393. Min Act: -0.1700

Data Index: 2044692 (Open Web Text)

Max Activating Token Index: 617

Text #6

Max Range: 6.0296. Min Range: -6.0296

Max Act: 5.6479. Min Act: -0.1700

Data Index: 5853915 (Open Web Text)

Max Activating Token Index: 753

Text #7

Max Range: 6.0296. Min Range: -6.0296

Max Act: 5.6827. Min Act: -0.1700

Data Index: 3425191 (Open Web Text)

Max Activating Token Index: 840

Text #8

Max Range: 6.0296. Min Range: -6.0296

Max Act: 5.6252. Min Act: -0.1700

Data Index: 8675693 (Open Web Text)

Max Activating Token Index: 636

Text #9

Max Range: 6.0296. Min Range: -6.0296

Max Act: 5.6587. Min Act: -0.1700

Data Index: 5421695 (Open Web Text)

Max Activating Token Index: 878

Text #10

Max Range: 6.0296. Min Range: -6.0296

Max Act: 5.6702. Min Act: -0.1700

Data Index: 2889033 (Open Web Text)

Max Activating Token Index: 890

Text #11

Max Range: 6.0296. Min Range: -6.0296

Max Act: 5.6271. Min Act: -0.1700

Data Index: 8359464 (Open Web Text)

Max Activating Token Index: 581

Text #12

Max Range: 6.0296. Min Range: -6.0296

Max Act: 5.6315. Min Act: -0.1700

Data Index: 6531881 (Open Web Text)

Max Activating Token Index: 738

Text #13

Max Range: 6.0296. Min Range: -6.0296

Max Act: 5.6306. Min Act: -0.1700

Data Index: 2814571 (Open Web Text)

Max Activating Token Index: 767

Text #14

Max Range: 6.0296. Min Range: -6.0296

Max Act: 5.5615. Min Act: -0.1700

Data Index: 1600574 (Open Web Text)

Max Activating Token Index: 508

Text #15

Max Range: 6.0296. Min Range: -6.0296

Max Act: 5.5858. Min Act: -0.1700

Data Index: 4753022 (Open Web Text)

Max Activating Token Index: 558

Text #16

Max Range: 6.0296. Min Range: -6.0296

Max Act: 5.5793. Min Act: -0.1700

Data Index: 3854665 (Open Web Text)

Max Activating Token Index: 895

Text #17

Max Range: 6.0296. Min Range: -6.0296

Max Act: 5.5831. Min Act: -0.1700

Data Index: 5999804 (Open Web Text)

Max Activating Token Index: 607

Text #18

Max Range: 6.0296. Min Range: -6.0296

Max Act: 5.5887. Min Act: -0.1700

Data Index: 5289205 (Open Web Text)

Max Activating Token Index: 634

Text #19

Max Range: 6.0296. Min Range: -6.0296

Max Act: 5.5383. Min Act: -0.1700

Data Index: 5185260 (Open Web Text)

Max Activating Token Index: 691