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

Dataset: Open Web Text

Neuron 2656 in Layer 4

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: 3.3667. Min Range: -3.3667

Max Act: 3.3667. Min Act: -0.1700

Data Index: 7433057 (Open Web Text)

Max Activating Token Index: 766

Text #1

Max Range: 3.3667. Min Range: -3.3667

Max Act: 3.3111. Min Act: -0.1700

Data Index: 6988884 (Open Web Text)

Max Activating Token Index: 725

Text #2

Max Range: 3.3667. Min Range: -3.3667

Max Act: 3.2557. Min Act: -0.1700

Data Index: 1692009 (Open Web Text)

Max Activating Token Index: 141

Text #3

Max Range: 3.3667. Min Range: -3.3667

Max Act: 3.2571. Min Act: -0.1700

Data Index: 3850580 (Open Web Text)

Max Activating Token Index: 241

Text #4

Max Range: 3.3667. Min Range: -3.3667

Max Act: 3.2366. Min Act: -0.1700

Data Index: 7433060 (Open Web Text)

Max Activating Token Index: 30

Text #5

Max Range: 3.3667. Min Range: -3.3667

Max Act: 3.2063. Min Act: -0.1699

Data Index: 2853499 (Open Web Text)

Max Activating Token Index: 1010

Text #6

Max Range: 3.3667. Min Range: -3.3667

Max Act: 3.2269. Min Act: -0.1700

Data Index: 6946511 (Open Web Text)

Max Activating Token Index: 416

Text #7

Max Range: 3.3667. Min Range: -3.3667

Max Act: 3.2155. Min Act: -0.1700

Data Index: 927781 (Open Web Text)

Max Activating Token Index: 112

Text #8

Max Range: 3.3667. Min Range: -3.3667

Max Act: 3.2271. Min Act: -0.1700

Data Index: 2948508 (Open Web Text)

Max Activating Token Index: 725

Text #9

Max Range: 3.3667. Min Range: -3.3667

Max Act: 3.1746. Min Act: -0.1700

Data Index: 6763521 (Open Web Text)

Max Activating Token Index: 47

Text #10

Max Range: 3.3667. Min Range: -3.3667

Max Act: 3.2005. Min Act: -0.1700

Data Index: 2977927 (Open Web Text)

Max Activating Token Index: 147

Text #11

Max Range: 3.3667. Min Range: -3.3667

Max Act: 3.2012. Min Act: -0.1700

Data Index: 5066391 (Open Web Text)

Max Activating Token Index: 761

Text #12

Max Range: 3.3667. Min Range: -3.3667

Max Act: 3.1755. Min Act: -0.1700

Data Index: 4925409 (Open Web Text)

Max Activating Token Index: 816

Text #13

Max Range: 3.3667. Min Range: -3.3667

Max Act: 3.1700. Min Act: -0.1700

Data Index: 5883557 (Open Web Text)

Max Activating Token Index: 623

Text #14

Max Range: 3.3667. Min Range: -3.3667

Max Act: 3.1569. Min Act: -0.1700

Data Index: 6155261 (Open Web Text)

Max Activating Token Index: 211

Text #15

Max Range: 3.3667. Min Range: -3.3667

Max Act: 3.1639. Min Act: -0.1700

Data Index: 2268999 (Open Web Text)

Max Activating Token Index: 17

Text #16

Max Range: 3.3667. Min Range: -3.3667

Max Act: 3.1490. Min Act: -0.1700

Data Index: 789558 (Open Web Text)

Max Activating Token Index: 66

Text #17

Max Range: 3.3667. Min Range: -3.3667

Max Act: 3.1343. Min Act: -0.1700

Data Index: 6901038 (Open Web Text)

Max Activating Token Index: 185

Text #18

Max Range: 3.3667. Min Range: -3.3667

Max Act: 3.1810. Min Act: -0.1700

Data Index: 2018219 (Open Web Text)

Max Activating Token Index: 73

Text #19

Max Range: 3.3667. Min Range: -3.3667

Max Act: 3.1553. Min Act: -0.1700

Data Index: 6459640 (Open Web Text)

Max Activating Token Index: 6