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

Dataset: Open Web Text

Neuron 3056 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: 4.6912. Min Range: -4.6912

Max Act: 4.6843. Min Act: -0.1700

Data Index: 3841139 (Open Web Text)

Max Activating Token Index: 831

Text #1

Max Range: 4.6912. Min Range: -4.6912

Max Act: 4.6912. Min Act: -0.1700

Data Index: 7083781 (Open Web Text)

Max Activating Token Index: 677

Text #2

Max Range: 4.6912. Min Range: -4.6912

Max Act: 4.6025. Min Act: -0.1700

Data Index: 2899892 (Open Web Text)

Max Activating Token Index: 585

Text #3

Max Range: 4.6912. Min Range: -4.6912

Max Act: 4.6338. Min Act: -0.1699

Data Index: 248081 (Open Web Text)

Max Activating Token Index: 349

Text #4

Max Range: 4.6912. Min Range: -4.6912

Max Act: 4.6344. Min Act: -0.1700

Data Index: 2904560 (Open Web Text)

Max Activating Token Index: 950

Text #5

Max Range: 4.6912. Min Range: -4.6912

Max Act: 4.6585. Min Act: -0.1700

Data Index: 5810910 (Open Web Text)

Max Activating Token Index: 77

Text #6

Max Range: 4.6912. Min Range: -4.6912

Max Act: 4.5966. Min Act: -0.1700

Data Index: 6622550 (Open Web Text)

Max Activating Token Index: 623

Text #7

Max Range: 4.6912. Min Range: -4.6912

Max Act: 4.5826. Min Act: -0.1700

Data Index: 509666 (Open Web Text)

Max Activating Token Index: 986

Text #8

Max Range: 4.6912. Min Range: -4.6912

Max Act: 4.5841. Min Act: -0.1700

Data Index: 792573 (Open Web Text)

Max Activating Token Index: 1000

Text #9

Max Range: 4.6912. Min Range: -4.6912

Max Act: 4.5856. Min Act: -0.1700

Data Index: 8330585 (Open Web Text)

Max Activating Token Index: 453

Text #10

Max Range: 4.6912. Min Range: -4.6912

Max Act: 4.5514. Min Act: -0.1700

Data Index: 6110779 (Open Web Text)

Max Activating Token Index: 462

Text #11

Max Range: 4.6912. Min Range: -4.6912

Max Act: 4.4729. Min Act: -0.1700

Data Index: 759489 (Open Web Text)

Max Activating Token Index: 439

Text #12

Max Range: 4.6912. Min Range: -4.6912

Max Act: 4.5362. Min Act: -0.1700

Data Index: 1144898 (Open Web Text)

Max Activating Token Index: 104

Text #13

Max Range: 4.6912. Min Range: -4.6912

Max Act: 4.5490. Min Act: -0.1700

Data Index: 4680804 (Open Web Text)

Max Activating Token Index: 369

Text #14

Max Range: 4.6912. Min Range: -4.6912

Max Act: 4.5463. Min Act: -0.1700

Data Index: 1231561 (Open Web Text)

Max Activating Token Index: 713

Text #15

Max Range: 4.6912. Min Range: -4.6912

Max Act: 4.5168. Min Act: -0.1700

Data Index: 2688812 (Open Web Text)

Max Activating Token Index: 958

Text #16

Max Range: 4.6912. Min Range: -4.6912

Max Act: 4.4775. Min Act: -0.1700

Data Index: 7122014 (Open Web Text)

Max Activating Token Index: 383

Text #17

Max Range: 4.6912. Min Range: -4.6912

Max Act: 4.5025. Min Act: -0.1700

Data Index: 1389096 (Open Web Text)

Max Activating Token Index: 514

Text #18

Max Range: 4.6912. Min Range: -4.6912

Max Act: 4.4646. Min Act: -0.1698

Data Index: 4072100 (Open Web Text)

Max Activating Token Index: 980

Text #19

Max Range: 4.6912. Min Range: -4.6912

Max Act: 4.4788. Min Act: -0.1700

Data Index: 3436794 (Open Web Text)

Max Activating Token Index: 404