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

Dataset: Open Web Text

Neuron 1512 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: 4.5599. Min Range: -4.5599

Max Act: 4.5599. Min Act: -0.1700

Data Index: 451982 (Open Web Text)

Max Activating Token Index: 401

Text #1

Max Range: 4.5599. Min Range: -4.5599

Max Act: 4.5065. Min Act: -0.1700

Data Index: 656707 (Open Web Text)

Max Activating Token Index: 690

Text #2

Max Range: 4.5599. Min Range: -4.5599

Max Act: 4.4558. Min Act: -0.1700

Data Index: 2926897 (Open Web Text)

Max Activating Token Index: 361

Text #3

Max Range: 4.5599. Min Range: -4.5599

Max Act: 4.4455. Min Act: -0.1700

Data Index: 2796373 (Open Web Text)

Max Activating Token Index: 1004

Text #4

Max Range: 4.5599. Min Range: -4.5599

Max Act: 4.4408. Min Act: -0.1700

Data Index: 7207242 (Open Web Text)

Max Activating Token Index: 612

Text #5

Max Range: 4.5599. Min Range: -4.5599

Max Act: 4.4255. Min Act: -0.1700

Data Index: 4972332 (Open Web Text)

Max Activating Token Index: 621

Text #6

Max Range: 4.5599. Min Range: -4.5599

Max Act: 4.3892. Min Act: -0.1700

Data Index: 2866776 (Open Web Text)

Max Activating Token Index: 432

Text #7

Max Range: 4.5599. Min Range: -4.5599

Max Act: 4.3799. Min Act: -0.1700

Data Index: 2929623 (Open Web Text)

Max Activating Token Index: 910

Text #8

Max Range: 4.5599. Min Range: -4.5599

Max Act: 4.3931. Min Act: -0.1700

Data Index: 4352596 (Open Web Text)

Max Activating Token Index: 282

Text #9

Max Range: 4.5599. Min Range: -4.5599

Max Act: 4.3910. Min Act: -0.1700

Data Index: 2399950 (Open Web Text)

Max Activating Token Index: 50

Text #10

Max Range: 4.5599. Min Range: -4.5599

Max Act: 4.3400. Min Act: -0.1700

Data Index: 6223479 (Open Web Text)

Max Activating Token Index: 689

Text #11

Max Range: 4.5599. Min Range: -4.5599

Max Act: 4.3440. Min Act: -0.1700

Data Index: 2661118 (Open Web Text)

Max Activating Token Index: 973

Text #12

Max Range: 4.5599. Min Range: -4.5599

Max Act: 4.3522. Min Act: -0.1700

Data Index: 6784811 (Open Web Text)

Max Activating Token Index: 411

Text #13

Max Range: 4.5599. Min Range: -4.5599

Max Act: 4.3112. Min Act: -0.1700

Data Index: 5478027 (Open Web Text)

Max Activating Token Index: 648

Text #14

Max Range: 4.5599. Min Range: -4.5599

Max Act: 4.3422. Min Act: -0.1700

Data Index: 3402502 (Open Web Text)

Max Activating Token Index: 736

Text #15

Max Range: 4.5599. Min Range: -4.5599

Max Act: 4.3240. Min Act: -0.1700

Data Index: 6339584 (Open Web Text)

Max Activating Token Index: 375

Text #16

Max Range: 4.5599. Min Range: -4.5599

Max Act: 4.3078. Min Act: -0.1700

Data Index: 3712487 (Open Web Text)

Max Activating Token Index: 778

Text #17

Max Range: 4.5599. Min Range: -4.5599

Max Act: 4.3179. Min Act: -0.1700

Data Index: 2712603 (Open Web Text)

Max Activating Token Index: 532

Text #18

Max Range: 4.5599. Min Range: -4.5599

Max Act: 4.3125. Min Act: -0.1700

Data Index: 4907510 (Open Web Text)

Max Activating Token Index: 608

Text #19

Max Range: 4.5599. Min Range: -4.5599

Max Act: 4.3180. Min Act: -0.1700

Data Index: 4902515 (Open Web Text)

Max Activating Token Index: 862