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

Dataset: Open Web Text

Neuron 1644 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: 3.8673. Min Range: -3.8673

Max Act: 3.8673. Min Act: -0.1700

Data Index: 6135380 (Open Web Text)

Max Activating Token Index: 683

Text #1

Max Range: 3.8673. Min Range: -3.8673

Max Act: 3.7288. Min Act: -0.1700

Data Index: 1367978 (Open Web Text)

Max Activating Token Index: 84

Text #2

Max Range: 3.8673. Min Range: -3.8673

Max Act: 3.7063. Min Act: -0.1700

Data Index: 2177475 (Open Web Text)

Max Activating Token Index: 405

Text #3

Max Range: 3.8673. Min Range: -3.8673

Max Act: 3.6910. Min Act: -0.1700

Data Index: 2032848 (Open Web Text)

Max Activating Token Index: 50

Text #4

Max Range: 3.8673. Min Range: -3.8673

Max Act: 3.6488. Min Act: -0.1700

Data Index: 4543799 (Open Web Text)

Max Activating Token Index: 289

Text #5

Max Range: 3.8673. Min Range: -3.8673

Max Act: 3.6032. Min Act: -0.1700

Data Index: 7845656 (Open Web Text)

Max Activating Token Index: 82

Text #6

Max Range: 3.8673. Min Range: -3.8673

Max Act: 3.6272. Min Act: -0.1700

Data Index: 1624188 (Open Web Text)

Max Activating Token Index: 1002

Text #7

Max Range: 3.8673. Min Range: -3.8673

Max Act: 3.5978. Min Act: -0.1700

Data Index: 959701 (Open Web Text)

Max Activating Token Index: 256

Text #8

Max Range: 3.8673. Min Range: -3.8673

Max Act: 3.5830. Min Act: -0.1700

Data Index: 676583 (Open Web Text)

Max Activating Token Index: 521

Text #9

Max Range: 3.8673. Min Range: -3.8673

Max Act: 3.5407. Min Act: -0.1700

Data Index: 985949 (Open Web Text)

Max Activating Token Index: 121

Text #10

Max Range: 3.8673. Min Range: -3.8673

Max Act: 3.5681. Min Act: -0.1700

Data Index: 7493209 (Open Web Text)

Max Activating Token Index: 189

Text #11

Max Range: 3.8673. Min Range: -3.8673

Max Act: 3.5727. Min Act: -0.1700

Data Index: 124841 (Open Web Text)

Max Activating Token Index: 724

Text #12

Max Range: 3.8673. Min Range: -3.8673

Max Act: 3.5517. Min Act: -0.1700

Data Index: 4533754 (Open Web Text)

Max Activating Token Index: 848

Text #13

Max Range: 3.8673. Min Range: -3.8673

Max Act: 3.5339. Min Act: -0.1700

Data Index: 2677364 (Open Web Text)

Max Activating Token Index: 332

Text #14

Max Range: 3.8673. Min Range: -3.8673

Max Act: 3.5383. Min Act: -0.1700

Data Index: 5774674 (Open Web Text)

Max Activating Token Index: 864

Text #15

Max Range: 3.8673. Min Range: -3.8673

Max Act: 3.5200. Min Act: -0.1700

Data Index: 2623010 (Open Web Text)

Max Activating Token Index: 228

Text #16

Max Range: 3.8673. Min Range: -3.8673

Max Act: 3.5123. Min Act: -0.1700

Data Index: 2662255 (Open Web Text)

Max Activating Token Index: 821

Text #17

Max Range: 3.8673. Min Range: -3.8673

Max Act: 3.5116. Min Act: -0.1700

Data Index: 5892578 (Open Web Text)

Max Activating Token Index: 352

Text #18

Max Range: 3.8673. Min Range: -3.8673

Max Act: 3.4932. Min Act: -0.1700

Data Index: 5006047 (Open Web Text)

Max Activating Token Index: 322

Text #19

Max Range: 3.8673. Min Range: -3.8673

Max Act: 3.4875. Min Act: -0.1700

Data Index: 6959679 (Open Web Text)

Max Activating Token Index: 779