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

Dataset: Open Web Text

Neuron 2741 in Layer 5

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: 4.4572. Min Range: -4.4572

Max Act: 4.4572. Min Act: -0.1700

Data Index: 7392751 (Open Web Text)

Max Activating Token Index: 784

Text #1

Max Range: 4.4572. Min Range: -4.4572

Max Act: 4.3703. Min Act: -0.1700

Data Index: 6971610 (Open Web Text)

Max Activating Token Index: 684

Text #2

Max Range: 4.4572. Min Range: -4.4572

Max Act: 4.3260. Min Act: -0.1700

Data Index: 2920959 (Open Web Text)

Max Activating Token Index: 920

Text #3

Max Range: 4.4572. Min Range: -4.4572

Max Act: 4.2682. Min Act: -0.1700

Data Index: 3876000 (Open Web Text)

Max Activating Token Index: 314

Text #4

Max Range: 4.4572. Min Range: -4.4572

Max Act: 4.2554. Min Act: -0.1700

Data Index: 7023248 (Open Web Text)

Max Activating Token Index: 270

Text #5

Max Range: 4.4572. Min Range: -4.4572

Max Act: 4.2383. Min Act: -0.1700

Data Index: 7507828 (Open Web Text)

Max Activating Token Index: 647

Text #6

Max Range: 4.4572. Min Range: -4.4572

Max Act: 4.1755. Min Act: -0.1700

Data Index: 3610686 (Open Web Text)

Max Activating Token Index: 371

Text #7

Max Range: 4.4572. Min Range: -4.4572

Max Act: 4.1606. Min Act: -0.1700

Data Index: 1748846 (Open Web Text)

Max Activating Token Index: 199

Text #8

Max Range: 4.4572. Min Range: -4.4572

Max Act: 4.1422. Min Act: -0.1700

Data Index: 3251103 (Open Web Text)

Max Activating Token Index: 363

Text #9

Max Range: 4.4572. Min Range: -4.4572

Max Act: 4.1819. Min Act: -0.1700

Data Index: 7392752 (Open Web Text)

Max Activating Token Index: 24

Text #10

Max Range: 4.4572. Min Range: -4.4572

Max Act: 4.1822. Min Act: -0.1700

Data Index: 7310537 (Open Web Text)

Max Activating Token Index: 837

Text #11

Max Range: 4.4572. Min Range: -4.4572

Max Act: 4.1773. Min Act: -0.1700

Data Index: 2941479 (Open Web Text)

Max Activating Token Index: 528

Text #12

Max Range: 4.4572. Min Range: -4.4572

Max Act: 4.1529. Min Act: -0.1700

Data Index: 6971609 (Open Web Text)

Max Activating Token Index: 716

Text #13

Max Range: 4.4572. Min Range: -4.4572

Max Act: 4.1577. Min Act: -0.1700

Data Index: 5934784 (Open Web Text)

Max Activating Token Index: 808

Text #14

Max Range: 4.4572. Min Range: -4.4572

Max Act: 4.1446. Min Act: -0.1700

Data Index: 704012 (Open Web Text)

Max Activating Token Index: 63

Text #15

Max Range: 4.4572. Min Range: -4.4572

Max Act: 4.1394. Min Act: -0.1700

Data Index: 6487800 (Open Web Text)

Max Activating Token Index: 869

Text #16

Max Range: 4.4572. Min Range: -4.4572

Max Act: 4.1445. Min Act: -0.1700

Data Index: 5934783 (Open Web Text)

Max Activating Token Index: 702

Text #17

Max Range: 4.4572. Min Range: -4.4572

Max Act: 4.1017. Min Act: -0.1700

Data Index: 3010929 (Open Web Text)

Max Activating Token Index: 7

Text #18

Max Range: 4.4572. Min Range: -4.4572

Max Act: 4.1111. Min Act: -0.1700

Data Index: 6104433 (Open Web Text)

Max Activating Token Index: 387

Text #19

Max Range: 4.4572. Min Range: -4.4572

Max Act: 4.0793. Min Act: -0.1700

Data Index: 6236823 (Open Web Text)

Max Activating Token Index: 651