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

Dataset: Open Web Text

Neuron 1478 in Layer 1

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: 1.6827. Min Range: -1.6827

Max Act: 1.6827. Min Act: -0.0656

Data Index: 7253638 (Open Web Text)

Max Activating Token Index: 510

Text #1

Max Range: 1.6827. Min Range: -1.6827

Max Act: 1.5937. Min Act: -0.1700

Data Index: 5148816 (Open Web Text)

Max Activating Token Index: 232

Text #2

Max Range: 1.6827. Min Range: -1.6827

Max Act: 1.5852. Min Act: -0.1700

Data Index: 969696 (Open Web Text)

Max Activating Token Index: 16

Text #3

Max Range: 1.6827. Min Range: -1.6827

Max Act: 1.5877. Min Act: -0.1693

Data Index: 6027238 (Open Web Text)

Max Activating Token Index: 494

Text #4

Max Range: 1.6827. Min Range: -1.6827

Max Act: 1.5868. Min Act: -0.1699

Data Index: 5257150 (Open Web Text)

Max Activating Token Index: 17

Text #5

Max Range: 1.6827. Min Range: -1.6827

Max Act: 1.5782. Min Act: -0.1619

Data Index: 7253639 (Open Web Text)

Max Activating Token Index: 163

Text #6

Max Range: 1.6827. Min Range: -1.6827

Max Act: 1.5783. Min Act: -0.1699

Data Index: 892584 (Open Web Text)

Max Activating Token Index: 269

Text #7

Max Range: 1.6827. Min Range: -1.6827

Max Act: 1.5747. Min Act: -0.1700

Data Index: 79696 (Open Web Text)

Max Activating Token Index: 879

Text #8

Max Range: 1.6827. Min Range: -1.6827

Max Act: 1.5778. Min Act: -0.1578

Data Index: 1444052 (Open Web Text)

Max Activating Token Index: 281

Text #9

Max Range: 1.6827. Min Range: -1.6827

Max Act: 1.5584. Min Act: -0.1696

Data Index: 1222478 (Open Web Text)

Max Activating Token Index: 144

Text #10

Max Range: 1.6827. Min Range: -1.6827

Max Act: 1.5599. Min Act: -0.1692

Data Index: 5463558 (Open Web Text)

Max Activating Token Index: 12

Text #11

Max Range: 1.6827. Min Range: -1.6827

Max Act: 1.5506. Min Act: -0.1697

Data Index: 1414270 (Open Web Text)

Max Activating Token Index: 355

Text #12

Max Range: 1.6827. Min Range: -1.6827

Max Act: 1.5544. Min Act: -0.1700

Data Index: 4847376 (Open Web Text)

Max Activating Token Index: 442

Text #13

Max Range: 1.6827. Min Range: -1.6827

Max Act: 1.5490. Min Act: -0.1594

Data Index: 1259401 (Open Web Text)

Max Activating Token Index: 350

Text #14

Max Range: 1.6827. Min Range: -1.6827

Max Act: 1.5412. Min Act: -0.1700

Data Index: 8380704 (Open Web Text)

Max Activating Token Index: 129

Text #15

Max Range: 1.6827. Min Range: -1.6827

Max Act: 1.5461. Min Act: -0.1700

Data Index: 202038 (Open Web Text)

Max Activating Token Index: 175

Text #16

Max Range: 1.6827. Min Range: -1.6827

Max Act: 1.5446. Min Act: -0.1700

Data Index: 1743011 (Open Web Text)

Max Activating Token Index: 172

Text #17

Max Range: 1.6827. Min Range: -1.6827

Max Act: 1.5310. Min Act: -0.1667

Data Index: 3219774 (Open Web Text)

Max Activating Token Index: 124

Text #18

Max Range: 1.6827. Min Range: -1.6827

Max Act: 1.5364. Min Act: -0.1669

Data Index: 1370663 (Open Web Text)

Max Activating Token Index: 52

Text #19

Max Range: 1.6827. Min Range: -1.6827

Max Act: 1.5327. Min Act: -0.1699

Data Index: 5452286 (Open Web Text)

Max Activating Token Index: 178