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

Dataset: Open Web Text

Neuron 2153 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: 1.6912. Min Range: -1.6912

Max Act: 1.6912. Min Act: -0.1700

Data Index: 6790572 (Open Web Text)

Max Activating Token Index: 501

Text #1

Max Range: 1.6912. Min Range: -1.6912

Max Act: 1.6819. Min Act: -0.1700

Data Index: 1631650 (Open Web Text)

Max Activating Token Index: 511

Text #2

Max Range: 1.6912. Min Range: -1.6912

Max Act: 1.6674. Min Act: -0.1700

Data Index: 6128962 (Open Web Text)

Max Activating Token Index: 616

Text #3

Max Range: 1.6912. Min Range: -1.6912

Max Act: 1.6716. Min Act: -0.1699

Data Index: 6110504 (Open Web Text)

Max Activating Token Index: 26

Text #4

Max Range: 1.6912. Min Range: -1.6912

Max Act: 1.6552. Min Act: -0.1700

Data Index: 3577893 (Open Web Text)

Max Activating Token Index: 9

Text #5

Max Range: 1.6912. Min Range: -1.6912

Max Act: 1.6581. Min Act: -0.1700

Data Index: 1335644 (Open Web Text)

Max Activating Token Index: 104

Text #6

Max Range: 1.6912. Min Range: -1.6912

Max Act: 1.6665. Min Act: -0.1700

Data Index: 2962743 (Open Web Text)

Max Activating Token Index: 291

Text #7

Max Range: 1.6912. Min Range: -1.6912

Max Act: 1.6769. Min Act: -0.1700

Data Index: 3389644 (Open Web Text)

Max Activating Token Index: 823

Text #8

Max Range: 1.6912. Min Range: -1.6912

Max Act: 1.6493. Min Act: -0.1700

Data Index: 4623160 (Open Web Text)

Max Activating Token Index: 905

Text #9

Max Range: 1.6912. Min Range: -1.6912

Max Act: 1.6659. Min Act: -0.1700

Data Index: 4058775 (Open Web Text)

Max Activating Token Index: 854

Text #10

Max Range: 1.6912. Min Range: -1.6912

Max Act: 1.6412. Min Act: -0.1700

Data Index: 7983183 (Open Web Text)

Max Activating Token Index: 7

Text #11

Max Range: 1.6912. Min Range: -1.6912

Max Act: 1.6451. Min Act: -0.1700

Data Index: 1746261 (Open Web Text)

Max Activating Token Index: 101

Text #12

Max Range: 1.6912. Min Range: -1.6912

Max Act: 1.6459. Min Act: -0.1700

Data Index: 3362862 (Open Web Text)

Max Activating Token Index: 80

Text #13

Max Range: 1.6912. Min Range: -1.6912

Max Act: 1.6320. Min Act: -0.1700

Data Index: 1740986 (Open Web Text)

Max Activating Token Index: 528

Text #14

Max Range: 1.6912. Min Range: -1.6912

Max Act: 1.6305. Min Act: -0.1700

Data Index: 2577002 (Open Web Text)

Max Activating Token Index: 254

Text #15

Max Range: 1.6912. Min Range: -1.6912

Max Act: 1.6374. Min Act: -0.1700

Data Index: 3864865 (Open Web Text)

Max Activating Token Index: 62

Text #16

Max Range: 1.6912. Min Range: -1.6912

Max Act: 1.6194. Min Act: -0.1698

Data Index: 2402817 (Open Web Text)

Max Activating Token Index: 75

Text #17

Max Range: 1.6912. Min Range: -1.6912

Max Act: 1.6162. Min Act: -0.1700

Data Index: 2248473 (Open Web Text)

Max Activating Token Index: 10

Text #18

Max Range: 1.6912. Min Range: -1.6912

Max Act: 1.6393. Min Act: -0.1700

Data Index: 2604011 (Open Web Text)

Max Activating Token Index: 484

Text #19

Max Range: 1.6912. Min Range: -1.6912

Max Act: 1.6197. Min Act: -0.1700

Data Index: 1700599 (Open Web Text)

Max Activating Token Index: 352