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

Dataset: Open Web Text

Neuron 393 in Layer 0

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: 3.6475. Min Range: -3.6475

Max Act: 3.6449. Min Act: -0.1700

Data Index: 7885637 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 3.6475. Min Range: -3.6475

Max Act: 3.6475. Min Act: -0.1700

Data Index: 300931 (Open Web Text)

Max Activating Token Index: 7

Text #2

Max Range: 3.6475. Min Range: -3.6475

Max Act: 3.6411. Min Act: -0.1700

Data Index: 5238709 (Open Web Text)

Max Activating Token Index: 11

Text #3

Max Range: 3.6475. Min Range: -3.6475

Max Act: 3.6268. Min Act: -0.1700

Data Index: 5744545 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 3.6475. Min Range: -3.6475

Max Act: 3.6283. Min Act: -0.1700

Data Index: 4758720 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 3.6475. Min Range: -3.6475

Max Act: 3.5965. Min Act: -0.1700

Data Index: 4866280 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 3.6475. Min Range: -3.6475

Max Act: 3.6173. Min Act: -0.1700

Data Index: 7735799 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 3.6475. Min Range: -3.6475

Max Act: 3.6166. Min Act: -0.1700

Data Index: 7318981 (Open Web Text)

Max Activating Token Index: 93

Text #8

Max Range: 3.6475. Min Range: -3.6475

Max Act: 3.6047. Min Act: -0.1700

Data Index: 6959625 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 3.6475. Min Range: -3.6475

Max Act: 3.6059. Min Act: -0.1700

Data Index: 595015 (Open Web Text)

Max Activating Token Index: 11

Text #10

Max Range: 3.6475. Min Range: -3.6475

Max Act: 3.6026. Min Act: -0.1700

Data Index: 8464077 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 3.6475. Min Range: -3.6475

Max Act: 3.6129. Min Act: -0.1700

Data Index: 5839055 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 3.6475. Min Range: -3.6475

Max Act: 3.5911. Min Act: -0.1700

Data Index: 8094699 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 3.6475. Min Range: -3.6475

Max Act: 3.5638. Min Act: -0.1699

Data Index: 6177544 (Open Web Text)

Max Activating Token Index: 44

Text #14

Max Range: 3.6475. Min Range: -3.6475

Max Act: 3.5637. Min Act: -0.1700

Data Index: 3821785 (Open Web Text)

Max Activating Token Index: 15

Text #15

Max Range: 3.6475. Min Range: -3.6475

Max Act: 3.5686. Min Act: -0.1700

Data Index: 1634374 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 3.6475. Min Range: -3.6475

Max Act: 3.5616. Min Act: -0.1700

Data Index: 1705969 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 3.6475. Min Range: -3.6475

Max Act: 3.5735. Min Act: -0.1700

Data Index: 1830192 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 3.6475. Min Range: -3.6475

Max Act: 3.5721. Min Act: -0.1700

Data Index: 7234523 (Open Web Text)

Max Activating Token Index: 12

Text #19

Max Range: 3.6475. Min Range: -3.6475

Max Act: 3.5618. Min Act: -0.1700

Data Index: 392883 (Open Web Text)

Max Activating Token Index: 7