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

Dataset: Open Web Text

Neuron 1277 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: 4.4405. Min Range: -4.4405

Max Act: 4.4274. Min Act: -0.1700

Data Index: 8463613 (Open Web Text)

Max Activating Token Index: 718

Text #1

Max Range: 4.4405. Min Range: -4.4405

Max Act: 4.4395. Min Act: -0.1700

Data Index: 268387 (Open Web Text)

Max Activating Token Index: 137

Text #2

Max Range: 4.4405. Min Range: -4.4405

Max Act: 4.4405. Min Act: -0.1700

Data Index: 3534239 (Open Web Text)

Max Activating Token Index: 647

Text #3

Max Range: 4.4405. Min Range: -4.4405

Max Act: 4.3743. Min Act: -0.1700

Data Index: 5296931 (Open Web Text)

Max Activating Token Index: 864

Text #4

Max Range: 4.4405. Min Range: -4.4405

Max Act: 4.3520. Min Act: -0.1700

Data Index: 4181116 (Open Web Text)

Max Activating Token Index: 719

Text #5

Max Range: 4.4405. Min Range: -4.4405

Max Act: 4.3668. Min Act: -0.1700

Data Index: 2114372 (Open Web Text)

Max Activating Token Index: 759

Text #6

Max Range: 4.4405. Min Range: -4.4405

Max Act: 4.3445. Min Act: -0.1700

Data Index: 2543733 (Open Web Text)

Max Activating Token Index: 53

Text #7

Max Range: 4.4405. Min Range: -4.4405

Max Act: 4.3323. Min Act: -0.1700

Data Index: 3666211 (Open Web Text)

Max Activating Token Index: 160

Text #8

Max Range: 4.4405. Min Range: -4.4405

Max Act: 4.2982. Min Act: -0.1700

Data Index: 6666867 (Open Web Text)

Max Activating Token Index: 886

Text #9

Max Range: 4.4405. Min Range: -4.4405

Max Act: 4.2899. Min Act: -0.1700

Data Index: 683996 (Open Web Text)

Max Activating Token Index: 473

Text #10

Max Range: 4.4405. Min Range: -4.4405

Max Act: 4.2728. Min Act: -0.1700

Data Index: 5406139 (Open Web Text)

Max Activating Token Index: 115

Text #11

Max Range: 4.4405. Min Range: -4.4405

Max Act: 4.2446. Min Act: -0.1700

Data Index: 4061910 (Open Web Text)

Max Activating Token Index: 389

Text #12

Max Range: 4.4405. Min Range: -4.4405

Max Act: 4.2894. Min Act: -0.1700

Data Index: 2154045 (Open Web Text)

Max Activating Token Index: 781

Text #13

Max Range: 4.4405. Min Range: -4.4405

Max Act: 4.2819. Min Act: -0.1700

Data Index: 5574520 (Open Web Text)

Max Activating Token Index: 182

Text #14

Max Range: 4.4405. Min Range: -4.4405

Max Act: 4.2838. Min Act: -0.1700

Data Index: 7460012 (Open Web Text)

Max Activating Token Index: 403

Text #15

Max Range: 4.4405. Min Range: -4.4405

Max Act: 4.2544. Min Act: -0.1700

Data Index: 2989718 (Open Web Text)

Max Activating Token Index: 953

Text #16

Max Range: 4.4405. Min Range: -4.4405

Max Act: 4.2478. Min Act: -0.1700

Data Index: 5748797 (Open Web Text)

Max Activating Token Index: 984

Text #17

Max Range: 4.4405. Min Range: -4.4405

Max Act: 4.2380. Min Act: -0.1700

Data Index: 4419682 (Open Web Text)

Max Activating Token Index: 967

Text #18

Max Range: 4.4405. Min Range: -4.4405

Max Act: 4.2541. Min Act: -0.1700

Data Index: 4507294 (Open Web Text)

Max Activating Token Index: 922

Text #19

Max Range: 4.4405. Min Range: -4.4405

Max Act: 4.2634. Min Act: -0.1700

Data Index: 4705744 (Open Web Text)

Max Activating Token Index: 903