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

Dataset: Open Web Text

Neuron 1674 in Layer 4

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: 2.5356. Min Range: -2.5356

Max Act: 2.5352. Min Act: -0.1697

Data Index: 857320 (Open Web Text)

Max Activating Token Index: 693

Text #1

Max Range: 2.5356. Min Range: -2.5356

Max Act: 2.5317. Min Act: -0.1662

Data Index: 2798671 (Open Web Text)

Max Activating Token Index: 815

Text #2

Max Range: 2.5356. Min Range: -2.5356

Max Act: 2.5199. Min Act: -0.1699

Data Index: 3823001 (Open Web Text)

Max Activating Token Index: 428

Text #3

Max Range: 2.5356. Min Range: -2.5356

Max Act: 2.5356. Min Act: -0.1682

Data Index: 7437698 (Open Web Text)

Max Activating Token Index: 793

Text #4

Max Range: 2.5356. Min Range: -2.5356

Max Act: 2.5049. Min Act: -0.1688

Data Index: 3563218 (Open Web Text)

Max Activating Token Index: 898

Text #5

Max Range: 2.5356. Min Range: -2.5356

Max Act: 2.5163. Min Act: -0.1700

Data Index: 5170243 (Open Web Text)

Max Activating Token Index: 715

Text #6

Max Range: 2.5356. Min Range: -2.5356

Max Act: 2.5012. Min Act: -0.1674

Data Index: 2407863 (Open Web Text)

Max Activating Token Index: 649

Text #7

Max Range: 2.5356. Min Range: -2.5356

Max Act: 2.4523. Min Act: -0.1689

Data Index: 8295004 (Open Web Text)

Max Activating Token Index: 706

Text #8

Max Range: 2.5356. Min Range: -2.5356

Max Act: 2.4525. Min Act: -0.1700

Data Index: 8427131 (Open Web Text)

Max Activating Token Index: 976

Text #9

Max Range: 2.5356. Min Range: -2.5356

Max Act: 2.4733. Min Act: -0.1675

Data Index: 2590833 (Open Web Text)

Max Activating Token Index: 785

Text #10

Max Range: 2.5356. Min Range: -2.5356

Max Act: 2.4816. Min Act: -0.1700

Data Index: 6277820 (Open Web Text)

Max Activating Token Index: 674

Text #11

Max Range: 2.5356. Min Range: -2.5356

Max Act: 2.4575. Min Act: -0.1674

Data Index: 3248135 (Open Web Text)

Max Activating Token Index: 775

Text #12

Max Range: 2.5356. Min Range: -2.5356

Max Act: 2.4571. Min Act: -0.1698

Data Index: 4445181 (Open Web Text)

Max Activating Token Index: 644

Text #13

Max Range: 2.5356. Min Range: -2.5356

Max Act: 2.4550. Min Act: -0.1591

Data Index: 4267448 (Open Web Text)

Max Activating Token Index: 439

Text #14

Max Range: 2.5356. Min Range: -2.5356

Max Act: 2.4583. Min Act: -0.1674

Data Index: 7336752 (Open Web Text)

Max Activating Token Index: 829

Text #15

Max Range: 2.5356. Min Range: -2.5356

Max Act: 2.4427. Min Act: -0.1683

Data Index: 2857836 (Open Web Text)

Max Activating Token Index: 975

Text #16

Max Range: 2.5356. Min Range: -2.5356

Max Act: 2.4646. Min Act: -0.1694

Data Index: 5602111 (Open Web Text)

Max Activating Token Index: 776

Text #17

Max Range: 2.5356. Min Range: -2.5356

Max Act: 2.4290. Min Act: -0.1700

Data Index: 1499430 (Open Web Text)

Max Activating Token Index: 688

Text #18

Max Range: 2.5356. Min Range: -2.5356

Max Act: 2.4452. Min Act: -0.1690

Data Index: 26913 (Open Web Text)

Max Activating Token Index: 876

Text #19

Max Range: 2.5356. Min Range: -2.5356

Max Act: 2.4409. Min Act: -0.1700

Data Index: 5788497 (Open Web Text)

Max Activating Token Index: 925