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

Dataset: Open Web Text

Neuron 2063 in Layer 2

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: 2.0496. Min Range: -2.0496

Max Act: 2.0379. Min Act: -0.1697

Data Index: 5017835 (Open Web Text)

Max Activating Token Index: 471

Text #1

Max Range: 2.0496. Min Range: -2.0496

Max Act: 2.0496. Min Act: -0.1700

Data Index: 1718292 (Open Web Text)

Max Activating Token Index: 824

Text #2

Max Range: 2.0496. Min Range: -2.0496

Max Act: 2.0091. Min Act: -0.1700

Data Index: 281559 (Open Web Text)

Max Activating Token Index: 914

Text #3

Max Range: 2.0496. Min Range: -2.0496

Max Act: 1.9924. Min Act: -0.1700

Data Index: 5288537 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 2.0496. Min Range: -2.0496

Max Act: 1.9915. Min Act: -0.1700

Data Index: 3639597 (Open Web Text)

Max Activating Token Index: 699

Text #5

Max Range: 2.0496. Min Range: -2.0496

Max Act: 1.9921. Min Act: -0.1698

Data Index: 6172354 (Open Web Text)

Max Activating Token Index: 29

Text #6

Max Range: 2.0496. Min Range: -2.0496

Max Act: 1.9661. Min Act: -0.1700

Data Index: 1582712 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 2.0496. Min Range: -2.0496

Max Act: 1.9630. Min Act: -0.1700

Data Index: 6953611 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 2.0496. Min Range: -2.0496

Max Act: 1.9664. Min Act: -0.1700

Data Index: 8068483 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 2.0496. Min Range: -2.0496

Max Act: 1.9676. Min Act: -0.1700

Data Index: 6888073 (Open Web Text)

Max Activating Token Index: 9

Text #10

Max Range: 2.0496. Min Range: -2.0496

Max Act: 1.9637. Min Act: -0.1700

Data Index: 6188532 (Open Web Text)

Max Activating Token Index: 9

Text #11

Max Range: 2.0496. Min Range: -2.0496

Max Act: 1.9509. Min Act: -0.1700

Data Index: 3433952 (Open Web Text)

Max Activating Token Index: 967

Text #12

Max Range: 2.0496. Min Range: -2.0496

Max Act: 1.9653. Min Act: -0.1700

Data Index: 6094601 (Open Web Text)

Max Activating Token Index: 323

Text #13

Max Range: 2.0496. Min Range: -2.0496

Max Act: 1.9505. Min Act: -0.1697

Data Index: 7952106 (Open Web Text)

Max Activating Token Index: 564

Text #14

Max Range: 2.0496. Min Range: -2.0496

Max Act: 1.9589. Min Act: -0.1700

Data Index: 5601980 (Open Web Text)

Max Activating Token Index: 9

Text #15

Max Range: 2.0496. Min Range: -2.0496

Max Act: 1.9447. Min Act: -0.1635

Data Index: 5859524 (Open Web Text)

Max Activating Token Index: 751

Text #16

Max Range: 2.0496. Min Range: -2.0496

Max Act: 1.9563. Min Act: -0.1700

Data Index: 5051971 (Open Web Text)

Max Activating Token Index: 77

Text #17

Max Range: 2.0496. Min Range: -2.0496

Max Act: 1.9523. Min Act: -0.1700

Data Index: 3500441 (Open Web Text)

Max Activating Token Index: 531

Text #18

Max Range: 2.0496. Min Range: -2.0496

Max Act: 1.9409. Min Act: -0.1649

Data Index: 641685 (Open Web Text)

Max Activating Token Index: 419

Text #19

Max Range: 2.0496. Min Range: -2.0496

Max Act: 1.9318. Min Act: -0.1700

Data Index: 4078968 (Open Web Text)

Max Activating Token Index: 254