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

Dataset: Open Web Text

Neuron 2267 in Layer 1

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: 1.4218. Min Range: -1.4218

Max Act: 1.4218. Min Act: -0.1700

Data Index: 1197817 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 1.4218. Min Range: -1.4218

Max Act: 1.4218. Min Act: -0.1700

Data Index: 340706 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 1.4218. Min Range: -1.4218

Max Act: 1.4218. Min Act: -0.1700

Data Index: 4244850 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 1.4218. Min Range: -1.4218

Max Act: 1.4218. Min Act: -0.1700

Data Index: 7216553 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 1.4218. Min Range: -1.4218

Max Act: 1.4218. Min Act: -0.1698

Data Index: 4582475 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 1.4218. Min Range: -1.4218

Max Act: 1.4218. Min Act: -0.1699

Data Index: 6104951 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 1.4218. Min Range: -1.4218

Max Act: 1.4081. Min Act: -0.1700

Data Index: 2282459 (Open Web Text)

Max Activating Token Index: 11

Text #7

Max Range: 1.4218. Min Range: -1.4218

Max Act: 1.4035. Min Act: -0.1700

Data Index: 6993528 (Open Web Text)

Max Activating Token Index: 8

Text #8

Max Range: 1.4218. Min Range: -1.4218

Max Act: 1.3961. Min Act: -0.1700

Data Index: 1891178 (Open Web Text)

Max Activating Token Index: 419

Text #9

Max Range: 1.4218. Min Range: -1.4218

Max Act: 1.4078. Min Act: -0.1700

Data Index: 3237677 (Open Web Text)

Max Activating Token Index: 26

Text #10

Max Range: 1.4218. Min Range: -1.4218

Max Act: 1.3906. Min Act: -0.1700

Data Index: 3516834 (Open Web Text)

Max Activating Token Index: 418

Text #11

Max Range: 1.4218. Min Range: -1.4218

Max Act: 1.3915. Min Act: -0.1692

Data Index: 4465394 (Open Web Text)

Max Activating Token Index: 501

Text #12

Max Range: 1.4218. Min Range: -1.4218

Max Act: 1.3837. Min Act: -0.1700

Data Index: 5712518 (Open Web Text)

Max Activating Token Index: 590

Text #13

Max Range: 1.4218. Min Range: -1.4218

Max Act: 1.3850. Min Act: -0.1699

Data Index: 4997383 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 1.4218. Min Range: -1.4218

Max Act: 1.3706. Min Act: -0.1683

Data Index: 8736456 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 1.4218. Min Range: -1.4218

Max Act: 1.3490. Min Act: -0.1700

Data Index: 880495 (Open Web Text)

Max Activating Token Index: 9

Text #16

Max Range: 1.4218. Min Range: -1.4218

Max Act: 1.3583. Min Act: -0.1696

Data Index: 3651474 (Open Web Text)

Max Activating Token Index: 125

Text #17

Max Range: 1.4218. Min Range: -1.4218

Max Act: 1.3561. Min Act: -0.1700

Data Index: 327073 (Open Web Text)

Max Activating Token Index: 47

Text #18

Max Range: 1.4218. Min Range: -1.4218

Max Act: 1.3491. Min Act: -0.1699

Data Index: 1018638 (Open Web Text)

Max Activating Token Index: 50

Text #19

Max Range: 1.4218. Min Range: -1.4218

Max Act: 1.3492. Min Act: -0.1553

Data Index: 545318 (Open Web Text)

Max Activating Token Index: 160