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

Dataset: Open Web Text

Neuron 1647 in Layer 0

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: 1.5450. Min Range: -1.5450

Max Act: 1.5450. Min Act: -0.1573

Data Index: 1500468 (Open Web Text)

Max Activating Token Index: 446

Text #1

Max Range: 1.5450. Min Range: -1.5450

Max Act: 1.5297. Min Act: -0.1494

Data Index: 7835348 (Open Web Text)

Max Activating Token Index: 656

Text #2

Max Range: 1.5450. Min Range: -1.5450

Max Act: 1.5133. Min Act: -0.1543

Data Index: 1718912 (Open Web Text)

Max Activating Token Index: 996

Text #3

Max Range: 1.5450. Min Range: -1.5450

Max Act: 1.5107. Min Act: -0.0519

Data Index: 3223920 (Open Web Text)

Max Activating Token Index: 537

Text #4

Max Range: 1.5450. Min Range: -1.5450

Max Act: 1.4977. Min Act: -0.1504

Data Index: 1710576 (Open Web Text)

Max Activating Token Index: 797

Text #5

Max Range: 1.5450. Min Range: -1.5450

Max Act: 1.4853. Min Act: -0.1490

Data Index: 8759284 (Open Web Text)

Max Activating Token Index: 659

Text #6

Max Range: 1.5450. Min Range: -1.5450

Max Act: 1.4938. Min Act: -0.1043

Data Index: 2434749 (Open Web Text)

Max Activating Token Index: 487

Text #7

Max Range: 1.5450. Min Range: -1.5450

Max Act: 1.4909. Min Act: -0.1501

Data Index: 6896119 (Open Web Text)

Max Activating Token Index: 935

Text #8

Max Range: 1.5450. Min Range: -1.5450

Max Act: 1.4834. Min Act: -0.1677

Data Index: 1648407 (Open Web Text)

Max Activating Token Index: 439

Text #9

Max Range: 1.5450. Min Range: -1.5450

Max Act: 1.4840. Min Act: -0.0812

Data Index: 6704896 (Open Web Text)

Max Activating Token Index: 349

Text #10

Max Range: 1.5450. Min Range: -1.5450

Max Act: 1.4880. Min Act: -0.0037

Data Index: 8592230 (Open Web Text)

Max Activating Token Index: 719

Text #11

Max Range: 1.5450. Min Range: -1.5450

Max Act: 1.4844. Min Act: -0.1469

Data Index: 7835349 (Open Web Text)

Max Activating Token Index: 132

Text #12

Max Range: 1.5450. Min Range: -1.5450

Max Act: 1.4836. Min Act: -0.1160

Data Index: 1203440 (Open Web Text)

Max Activating Token Index: 893

Text #13

Max Range: 1.5450. Min Range: -1.5450

Max Act: 1.4690. Min Act: -0.1452

Data Index: 4238025 (Open Web Text)

Max Activating Token Index: 75

Text #14

Max Range: 1.5450. Min Range: -1.5450

Max Act: 1.4721. Min Act: -0.1663

Data Index: 5861483 (Open Web Text)

Max Activating Token Index: 133

Text #15

Max Range: 1.5450. Min Range: -1.5450

Max Act: 1.4695. Min Act: -0.0605

Data Index: 1710578 (Open Web Text)

Max Activating Token Index: 162

Text #16

Max Range: 1.5450. Min Range: -1.5450

Max Act: 1.4646. Min Act: -0.1325

Data Index: 5832924 (Open Web Text)

Max Activating Token Index: 829

Text #17

Max Range: 1.5450. Min Range: -1.5450

Max Act: 1.4594. Min Act: -0.1136

Data Index: 5784586 (Open Web Text)

Max Activating Token Index: 716

Text #18

Max Range: 1.5450. Min Range: -1.5450

Max Act: 1.4582. Min Act: -0.1549

Data Index: 1116369 (Open Web Text)

Max Activating Token Index: 529

Text #19

Max Range: 1.5450. Min Range: -1.5450

Max Act: 1.4643. Min Act: -0.1693

Data Index: 583922 (Open Web Text)

Max Activating Token Index: 390