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

Dataset: Open Web Text

Neuron 2797 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: 3.6490. Min Range: -3.6490

Max Act: 3.6490. Min Act: -0.1700

Data Index: 82145 (Open Web Text)

Max Activating Token Index: 272

Text #1

Max Range: 3.6490. Min Range: -3.6490

Max Act: 3.6111. Min Act: -0.1700

Data Index: 5631782 (Open Web Text)

Max Activating Token Index: 368

Text #2

Max Range: 3.6490. Min Range: -3.6490

Max Act: 3.5890. Min Act: -0.1700

Data Index: 2622993 (Open Web Text)

Max Activating Token Index: 642

Text #3

Max Range: 3.6490. Min Range: -3.6490

Max Act: 3.5682. Min Act: -0.1700

Data Index: 780473 (Open Web Text)

Max Activating Token Index: 822

Text #4

Max Range: 3.6490. Min Range: -3.6490

Max Act: 3.5679. Min Act: -0.1700

Data Index: 6252490 (Open Web Text)

Max Activating Token Index: 127

Text #5

Max Range: 3.6490. Min Range: -3.6490

Max Act: 3.5520. Min Act: -0.1700

Data Index: 4861765 (Open Web Text)

Max Activating Token Index: 1002

Text #6

Max Range: 3.6490. Min Range: -3.6490

Max Act: 3.5335. Min Act: -0.1700

Data Index: 7380609 (Open Web Text)

Max Activating Token Index: 966

Text #7

Max Range: 3.6490. Min Range: -3.6490

Max Act: 3.5358. Min Act: -0.1700

Data Index: 7820279 (Open Web Text)

Max Activating Token Index: 900

Text #8

Max Range: 3.6490. Min Range: -3.6490

Max Act: 3.5344. Min Act: -0.1700

Data Index: 8103493 (Open Web Text)

Max Activating Token Index: 169

Text #9

Max Range: 3.6490. Min Range: -3.6490

Max Act: 3.5348. Min Act: -0.1700

Data Index: 3260973 (Open Web Text)

Max Activating Token Index: 579

Text #10

Max Range: 3.6490. Min Range: -3.6490

Max Act: 3.5114. Min Act: -0.1700

Data Index: 4201689 (Open Web Text)

Max Activating Token Index: 743

Text #11

Max Range: 3.6490. Min Range: -3.6490

Max Act: 3.5292. Min Act: -0.1700

Data Index: 6459113 (Open Web Text)

Max Activating Token Index: 738

Text #12

Max Range: 3.6490. Min Range: -3.6490

Max Act: 3.4847. Min Act: -0.1700

Data Index: 3133153 (Open Web Text)

Max Activating Token Index: 544

Text #13

Max Range: 3.6490. Min Range: -3.6490

Max Act: 3.4894. Min Act: -0.1700

Data Index: 6747110 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 3.6490. Min Range: -3.6490

Max Act: 3.4753. Min Act: -0.1700

Data Index: 7223921 (Open Web Text)

Max Activating Token Index: 154

Text #15

Max Range: 3.6490. Min Range: -3.6490

Max Act: 3.4733. Min Act: -0.1700

Data Index: 5906946 (Open Web Text)

Max Activating Token Index: 522

Text #16

Max Range: 3.6490. Min Range: -3.6490

Max Act: 3.4478. Min Act: -0.1700

Data Index: 6823763 (Open Web Text)

Max Activating Token Index: 400

Text #17

Max Range: 3.6490. Min Range: -3.6490

Max Act: 3.4632. Min Act: -0.1700

Data Index: 4548568 (Open Web Text)

Max Activating Token Index: 994

Text #18

Max Range: 3.6490. Min Range: -3.6490

Max Act: 3.4164. Min Act: -0.1700

Data Index: 6138565 (Open Web Text)

Max Activating Token Index: 160

Text #19

Max Range: 3.6490. Min Range: -3.6490

Max Act: 3.4601. Min Act: -0.1700

Data Index: 5542161 (Open Web Text)

Max Activating Token Index: 785