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

Dataset: Open Web Text

Neuron 2682 in Layer 3

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: 6.4586. Min Range: -6.4586

Max Act: 6.4518. Min Act: -0.1700

Data Index: 7098345 (Open Web Text)

Max Activating Token Index: 679

Text #1

Max Range: 6.4586. Min Range: -6.4586

Max Act: 6.4586. Min Act: -0.1700

Data Index: 1048570 (Open Web Text)

Max Activating Token Index: 199

Text #2

Max Range: 6.4586. Min Range: -6.4586

Max Act: 6.4533. Min Act: -0.1700

Data Index: 8309873 (Open Web Text)

Max Activating Token Index: 87

Text #3

Max Range: 6.4586. Min Range: -6.4586

Max Act: 6.3907. Min Act: -0.1700

Data Index: 4152680 (Open Web Text)

Max Activating Token Index: 616

Text #4

Max Range: 6.4586. Min Range: -6.4586

Max Act: 6.4069. Min Act: -0.1700

Data Index: 4007567 (Open Web Text)

Max Activating Token Index: 207

Text #5

Max Range: 6.4586. Min Range: -6.4586

Max Act: 6.3659. Min Act: -0.1700

Data Index: 4458325 (Open Web Text)

Max Activating Token Index: 732

Text #6

Max Range: 6.4586. Min Range: -6.4586

Max Act: 6.3580. Min Act: -0.1700

Data Index: 2052549 (Open Web Text)

Max Activating Token Index: 723

Text #7

Max Range: 6.4586. Min Range: -6.4586

Max Act: 6.3155. Min Act: -0.1700

Data Index: 5059392 (Open Web Text)

Max Activating Token Index: 629

Text #8

Max Range: 6.4586. Min Range: -6.4586

Max Act: 6.3661. Min Act: -0.1700

Data Index: 319696 (Open Web Text)

Max Activating Token Index: 872

Text #9

Max Range: 6.4586. Min Range: -6.4586

Max Act: 6.3551. Min Act: -0.1700

Data Index: 573946 (Open Web Text)

Max Activating Token Index: 499

Text #10

Max Range: 6.4586. Min Range: -6.4586

Max Act: 6.2961. Min Act: -0.1700

Data Index: 4576879 (Open Web Text)

Max Activating Token Index: 505

Text #11

Max Range: 6.4586. Min Range: -6.4586

Max Act: 6.2907. Min Act: -0.1700

Data Index: 4004356 (Open Web Text)

Max Activating Token Index: 408

Text #12

Max Range: 6.4586. Min Range: -6.4586

Max Act: 6.2817. Min Act: -0.1700

Data Index: 7362512 (Open Web Text)

Max Activating Token Index: 518

Text #13

Max Range: 6.4586. Min Range: -6.4586

Max Act: 6.2970. Min Act: -0.1700

Data Index: 5154799 (Open Web Text)

Max Activating Token Index: 765

Text #14

Max Range: 6.4586. Min Range: -6.4586

Max Act: 6.3098. Min Act: -0.1700

Data Index: 4306529 (Open Web Text)

Max Activating Token Index: 545

Text #15

Max Range: 6.4586. Min Range: -6.4586

Max Act: 6.2436. Min Act: -0.1700

Data Index: 999792 (Open Web Text)

Max Activating Token Index: 363

Text #16

Max Range: 6.4586. Min Range: -6.4586

Max Act: 6.2586. Min Act: -0.1700

Data Index: 3358450 (Open Web Text)

Max Activating Token Index: 68

Text #17

Max Range: 6.4586. Min Range: -6.4586

Max Act: 6.2627. Min Act: -0.1700

Data Index: 6065576 (Open Web Text)

Max Activating Token Index: 509

Text #18

Max Range: 6.4586. Min Range: -6.4586

Max Act: 6.2483. Min Act: -0.1700

Data Index: 4941695 (Open Web Text)

Max Activating Token Index: 318

Text #19

Max Range: 6.4586. Min Range: -6.4586

Max Act: 6.2267. Min Act: -0.1700

Data Index: 6449048 (Open Web Text)

Max Activating Token Index: 359