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

Dataset: Open Web Text

Neuron 2907 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: 4.7789. Min Range: -4.7789

Max Act: 4.7789. Min Act: -0.1700

Data Index: 1894301 (Open Web Text)

Max Activating Token Index: 246

Text #1

Max Range: 4.7789. Min Range: -4.7789

Max Act: 4.7685. Min Act: -0.1700

Data Index: 3644109 (Open Web Text)

Max Activating Token Index: 622

Text #2

Max Range: 4.7789. Min Range: -4.7789

Max Act: 4.7464. Min Act: -0.1700

Data Index: 7818629 (Open Web Text)

Max Activating Token Index: 559

Text #3

Max Range: 4.7789. Min Range: -4.7789

Max Act: 4.7378. Min Act: -0.1700

Data Index: 485427 (Open Web Text)

Max Activating Token Index: 10

Text #4

Max Range: 4.7789. Min Range: -4.7789

Max Act: 4.7528. Min Act: -0.1700

Data Index: 1918678 (Open Web Text)

Max Activating Token Index: 10

Text #5

Max Range: 4.7789. Min Range: -4.7789

Max Act: 4.7422. Min Act: -0.1700

Data Index: 2187639 (Open Web Text)

Max Activating Token Index: 93

Text #6

Max Range: 4.7789. Min Range: -4.7789

Max Act: 4.7588. Min Act: -0.1700

Data Index: 5402253 (Open Web Text)

Max Activating Token Index: 95

Text #7

Max Range: 4.7789. Min Range: -4.7789

Max Act: 4.7423. Min Act: -0.1700

Data Index: 5084836 (Open Web Text)

Max Activating Token Index: 304

Text #8

Max Range: 4.7789. Min Range: -4.7789

Max Act: 4.7417. Min Act: -0.1700

Data Index: 99254 (Open Web Text)

Max Activating Token Index: 256

Text #9

Max Range: 4.7789. Min Range: -4.7789

Max Act: 4.6938. Min Act: -0.1700

Data Index: 3747577 (Open Web Text)

Max Activating Token Index: 9

Text #10

Max Range: 4.7789. Min Range: -4.7789

Max Act: 4.6947. Min Act: -0.1700

Data Index: 1058105 (Open Web Text)

Max Activating Token Index: 602

Text #11

Max Range: 4.7789. Min Range: -4.7789

Max Act: 4.7185. Min Act: -0.1700

Data Index: 5115906 (Open Web Text)

Max Activating Token Index: 11

Text #12

Max Range: 4.7789. Min Range: -4.7789

Max Act: 4.7263. Min Act: -0.1700

Data Index: 2593698 (Open Web Text)

Max Activating Token Index: 220

Text #13

Max Range: 4.7789. Min Range: -4.7789

Max Act: 4.7003. Min Act: -0.1700

Data Index: 4105644 (Open Web Text)

Max Activating Token Index: 10

Text #14

Max Range: 4.7789. Min Range: -4.7789

Max Act: 4.7079. Min Act: -0.1700

Data Index: 3888191 (Open Web Text)

Max Activating Token Index: 561

Text #15

Max Range: 4.7789. Min Range: -4.7789

Max Act: 4.7174. Min Act: -0.1700

Data Index: 2256011 (Open Web Text)

Max Activating Token Index: 432

Text #16

Max Range: 4.7789. Min Range: -4.7789

Max Act: 4.7199. Min Act: -0.1700

Data Index: 366954 (Open Web Text)

Max Activating Token Index: 482

Text #17

Max Range: 4.7789. Min Range: -4.7789

Max Act: 4.7388. Min Act: -0.1698

Data Index: 366957 (Open Web Text)

Max Activating Token Index: 585

Text #18

Max Range: 4.7789. Min Range: -4.7789

Max Act: 4.7232. Min Act: -0.1700

Data Index: 535785 (Open Web Text)

Max Activating Token Index: 640

Text #19

Max Range: 4.7789. Min Range: -4.7789

Max Act: 4.7103. Min Act: -0.1700

Data Index: 37677 (Open Web Text)

Max Activating Token Index: 31