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

Dataset: Open Web Text

Neuron 2900 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: 3.8741. Min Range: -3.8741

Max Act: 3.8741. Min Act: -0.1700

Data Index: 6791153 (Open Web Text)

Max Activating Token Index: 969

Text #1

Max Range: 3.8741. Min Range: -3.8741

Max Act: 3.8349. Min Act: -0.1700

Data Index: 6791154 (Open Web Text)

Max Activating Token Index: 244

Text #2

Max Range: 3.8741. Min Range: -3.8741

Max Act: 3.6900. Min Act: -0.1700

Data Index: 5208123 (Open Web Text)

Max Activating Token Index: 320

Text #3

Max Range: 3.8741. Min Range: -3.8741

Max Act: 3.6647. Min Act: -0.1700

Data Index: 8766429 (Open Web Text)

Max Activating Token Index: 429

Text #4

Max Range: 3.8741. Min Range: -3.8741

Max Act: 3.6528. Min Act: -0.1700

Data Index: 442287 (Open Web Text)

Max Activating Token Index: 639

Text #5

Max Range: 3.8741. Min Range: -3.8741

Max Act: 3.6212. Min Act: -0.1700

Data Index: 8407877 (Open Web Text)

Max Activating Token Index: 813

Text #6

Max Range: 3.8741. Min Range: -3.8741

Max Act: 3.6008. Min Act: -0.1700

Data Index: 873542 (Open Web Text)

Max Activating Token Index: 685

Text #7

Max Range: 3.8741. Min Range: -3.8741

Max Act: 3.6447. Min Act: -0.1700

Data Index: 4762454 (Open Web Text)

Max Activating Token Index: 493

Text #8

Max Range: 3.8741. Min Range: -3.8741

Max Act: 3.5711. Min Act: -0.1700

Data Index: 8721998 (Open Web Text)

Max Activating Token Index: 385

Text #9

Max Range: 3.8741. Min Range: -3.8741

Max Act: 3.5954. Min Act: -0.1700

Data Index: 1067142 (Open Web Text)

Max Activating Token Index: 683

Text #10

Max Range: 3.8741. Min Range: -3.8741

Max Act: 3.5614. Min Act: -0.1700

Data Index: 7535440 (Open Web Text)

Max Activating Token Index: 434

Text #11

Max Range: 3.8741. Min Range: -3.8741

Max Act: 3.5608. Min Act: -0.1700

Data Index: 6531168 (Open Web Text)

Max Activating Token Index: 777

Text #12

Max Range: 3.8741. Min Range: -3.8741

Max Act: 3.5629. Min Act: -0.1700

Data Index: 3293017 (Open Web Text)

Max Activating Token Index: 553

Text #13

Max Range: 3.8741. Min Range: -3.8741

Max Act: 3.5391. Min Act: -0.1700

Data Index: 3646454 (Open Web Text)

Max Activating Token Index: 349

Text #14

Max Range: 3.8741. Min Range: -3.8741

Max Act: 3.5360. Min Act: -0.1700

Data Index: 8152534 (Open Web Text)

Max Activating Token Index: 809

Text #15

Max Range: 3.8741. Min Range: -3.8741

Max Act: 3.5675. Min Act: -0.1700

Data Index: 377245 (Open Web Text)

Max Activating Token Index: 225

Text #16

Max Range: 3.8741. Min Range: -3.8741

Max Act: 3.5064. Min Act: -0.1700

Data Index: 6199669 (Open Web Text)

Max Activating Token Index: 895

Text #17

Max Range: 3.8741. Min Range: -3.8741

Max Act: 3.5453. Min Act: -0.1700

Data Index: 5384412 (Open Web Text)

Max Activating Token Index: 557

Text #18

Max Range: 3.8741. Min Range: -3.8741

Max Act: 3.5104. Min Act: -0.1700

Data Index: 2674768 (Open Web Text)

Max Activating Token Index: 850

Text #19

Max Range: 3.8741. Min Range: -3.8741

Max Act: 3.5128. Min Act: -0.1700

Data Index: 3684663 (Open Web Text)

Max Activating Token Index: 831