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

Dataset: Open Web Text

Neuron 567 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: 1.5642. Min Range: -1.5642

Max Act: 1.5642. Min Act: -0.1698

Data Index: 2542465 (Open Web Text)

Max Activating Token Index: 50

Text #1

Max Range: 1.5642. Min Range: -1.5642

Max Act: 1.4989. Min Act: -0.1694

Data Index: 1072910 (Open Web Text)

Max Activating Token Index: 55

Text #2

Max Range: 1.5642. Min Range: -1.5642

Max Act: 1.4591. Min Act: -0.1700

Data Index: 1066094 (Open Web Text)

Max Activating Token Index: 23

Text #3

Max Range: 1.5642. Min Range: -1.5642

Max Act: 1.4227. Min Act: -0.1646

Data Index: 3585495 (Open Web Text)

Max Activating Token Index: 821

Text #4

Max Range: 1.5642. Min Range: -1.5642

Max Act: 1.3676. Min Act: -0.1453

Data Index: 8305856 (Open Web Text)

Max Activating Token Index: 176

Text #5

Max Range: 1.5642. Min Range: -1.5642

Max Act: 1.3565. Min Act: -0.1700

Data Index: 3585483 (Open Web Text)

Max Activating Token Index: 778

Text #6

Max Range: 1.5642. Min Range: -1.5642

Max Act: 1.3526. Min Act: -0.1679

Data Index: 1224272 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 1.5642. Min Range: -1.5642

Max Act: 1.3742. Min Act: -0.1700

Data Index: 3585519 (Open Web Text)

Max Activating Token Index: 886

Text #8

Max Range: 1.5642. Min Range: -1.5642

Max Act: 1.3438. Min Act: -0.1318

Data Index: 5525495 (Open Web Text)

Max Activating Token Index: 392

Text #9

Max Range: 1.5642. Min Range: -1.5642

Max Act: 1.3573. Min Act: -0.1457

Data Index: 474766 (Open Web Text)

Max Activating Token Index: 925

Text #10

Max Range: 1.5642. Min Range: -1.5642

Max Act: 1.3418. Min Act: -0.1367

Data Index: 3941991 (Open Web Text)

Max Activating Token Index: 398

Text #11

Max Range: 1.5642. Min Range: -1.5642

Max Act: 1.3179. Min Act: -0.1669

Data Index: 474767 (Open Web Text)

Max Activating Token Index: 379

Text #12

Max Range: 1.5642. Min Range: -1.5642

Max Act: 1.3045. Min Act: -0.1697

Data Index: 3585514 (Open Web Text)

Max Activating Token Index: 897

Text #13

Max Range: 1.5642. Min Range: -1.5642

Max Act: 1.3125. Min Act: -0.1314

Data Index: 2783623 (Open Web Text)

Max Activating Token Index: 346

Text #14

Max Range: 1.5642. Min Range: -1.5642

Max Act: 1.3089. Min Act: -0.1684

Data Index: 2711439 (Open Web Text)

Max Activating Token Index: 560

Text #15

Max Range: 1.5642. Min Range: -1.5642

Max Act: 1.2881. Min Act: -0.1700

Data Index: 4715675 (Open Web Text)

Max Activating Token Index: 77

Text #16

Max Range: 1.5642. Min Range: -1.5642

Max Act: 1.2920. Min Act: -0.1687

Data Index: 3585492 (Open Web Text)

Max Activating Token Index: 786

Text #17

Max Range: 1.5642. Min Range: -1.5642

Max Act: 1.2727. Min Act: -0.1696

Data Index: 5525191 (Open Web Text)

Max Activating Token Index: 903

Text #18

Max Range: 1.5642. Min Range: -1.5642

Max Act: 1.2700. Min Act: -0.1320

Data Index: 6021914 (Open Web Text)

Max Activating Token Index: 132

Text #19

Max Range: 1.5642. Min Range: -1.5642

Max Act: 1.2658. Min Act: -0.1675

Data Index: 1277379 (Open Web Text)

Max Activating Token Index: 57