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

Dataset: Open Web Text

Neuron 375 in Layer 2

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: 3.3017. Min Range: -3.3017

Max Act: 3.3017. Min Act: -0.1700

Data Index: 480446 (Open Web Text)

Max Activating Token Index: 467

Text #1

Max Range: 3.3017. Min Range: -3.3017

Max Act: 3.2584. Min Act: -0.1700

Data Index: 2441862 (Open Web Text)

Max Activating Token Index: 482

Text #2

Max Range: 3.3017. Min Range: -3.3017

Max Act: 3.2149. Min Act: -0.1700

Data Index: 2983435 (Open Web Text)

Max Activating Token Index: 475

Text #3

Max Range: 3.3017. Min Range: -3.3017

Max Act: 3.2117. Min Act: -0.1700

Data Index: 5337035 (Open Web Text)

Max Activating Token Index: 622

Text #4

Max Range: 3.3017. Min Range: -3.3017

Max Act: 3.1984. Min Act: -0.1700

Data Index: 6906599 (Open Web Text)

Max Activating Token Index: 498

Text #5

Max Range: 3.3017. Min Range: -3.3017

Max Act: 3.1687. Min Act: -0.1700

Data Index: 2338356 (Open Web Text)

Max Activating Token Index: 453

Text #6

Max Range: 3.3017. Min Range: -3.3017

Max Act: 3.1858. Min Act: -0.1700

Data Index: 6197666 (Open Web Text)

Max Activating Token Index: 470

Text #7

Max Range: 3.3017. Min Range: -3.3017

Max Act: 3.1779. Min Act: -0.1700

Data Index: 156706 (Open Web Text)

Max Activating Token Index: 21

Text #8

Max Range: 3.3017. Min Range: -3.3017

Max Act: 3.1846. Min Act: -0.1700

Data Index: 5628267 (Open Web Text)

Max Activating Token Index: 719

Text #9

Max Range: 3.3017. Min Range: -3.3017

Max Act: 3.1808. Min Act: -0.1700

Data Index: 5180634 (Open Web Text)

Max Activating Token Index: 625

Text #10

Max Range: 3.3017. Min Range: -3.3017

Max Act: 3.1654. Min Act: -0.1700

Data Index: 7084090 (Open Web Text)

Max Activating Token Index: 65

Text #11

Max Range: 3.3017. Min Range: -3.3017

Max Act: 3.1719. Min Act: -0.1700

Data Index: 4478580 (Open Web Text)

Max Activating Token Index: 1012

Text #12

Max Range: 3.3017. Min Range: -3.3017

Max Act: 3.1557. Min Act: -0.1700

Data Index: 2565733 (Open Web Text)

Max Activating Token Index: 101

Text #13

Max Range: 3.3017. Min Range: -3.3017

Max Act: 3.1820. Min Act: -0.1700

Data Index: 2016631 (Open Web Text)

Max Activating Token Index: 624

Text #14

Max Range: 3.3017. Min Range: -3.3017

Max Act: 3.1561. Min Act: -0.1700

Data Index: 7453966 (Open Web Text)

Max Activating Token Index: 849

Text #15

Max Range: 3.3017. Min Range: -3.3017

Max Act: 3.1549. Min Act: -0.1700

Data Index: 4269411 (Open Web Text)

Max Activating Token Index: 445

Text #16

Max Range: 3.3017. Min Range: -3.3017

Max Act: 3.1722. Min Act: -0.1700

Data Index: 500196 (Open Web Text)

Max Activating Token Index: 76

Text #17

Max Range: 3.3017. Min Range: -3.3017

Max Act: 3.1573. Min Act: -0.1700

Data Index: 7046648 (Open Web Text)

Max Activating Token Index: 469

Text #18

Max Range: 3.3017. Min Range: -3.3017

Max Act: 3.1465. Min Act: -0.1700

Data Index: 3060747 (Open Web Text)

Max Activating Token Index: 582

Text #19

Max Range: 3.3017. Min Range: -3.3017

Max Act: 3.1445. Min Act: -0.1700

Data Index: 4997360 (Open Web Text)

Max Activating Token Index: 630