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

Dataset: Open Web Text

Neuron 418 in Layer 3

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: 4.6118. Min Range: -4.6118

Max Act: 4.6118. Min Act: -0.1700

Data Index: 3060066 (Open Web Text)

Max Activating Token Index: 40

Text #1

Max Range: 4.6118. Min Range: -4.6118

Max Act: 4.4152. Min Act: -0.1700

Data Index: 8492807 (Open Web Text)

Max Activating Token Index: 981

Text #2

Max Range: 4.6118. Min Range: -4.6118

Max Act: 4.3845. Min Act: -0.1700

Data Index: 8554124 (Open Web Text)

Max Activating Token Index: 400

Text #3

Max Range: 4.6118. Min Range: -4.6118

Max Act: 4.2962. Min Act: -0.1700

Data Index: 8410520 (Open Web Text)

Max Activating Token Index: 88

Text #4

Max Range: 4.6118. Min Range: -4.6118

Max Act: 4.3172. Min Act: -0.1700

Data Index: 995708 (Open Web Text)

Max Activating Token Index: 109

Text #5

Max Range: 4.6118. Min Range: -4.6118

Max Act: 4.2810. Min Act: -0.1700

Data Index: 4774967 (Open Web Text)

Max Activating Token Index: 1001

Text #6

Max Range: 4.6118. Min Range: -4.6118

Max Act: 4.3045. Min Act: -0.1700

Data Index: 266121 (Open Web Text)

Max Activating Token Index: 180

Text #7

Max Range: 4.6118. Min Range: -4.6118

Max Act: 4.3269. Min Act: -0.1700

Data Index: 2977379 (Open Web Text)

Max Activating Token Index: 945

Text #8

Max Range: 4.6118. Min Range: -4.6118

Max Act: 4.3282. Min Act: -0.1700

Data Index: 96944 (Open Web Text)

Max Activating Token Index: 251

Text #9

Max Range: 4.6118. Min Range: -4.6118

Max Act: 4.3057. Min Act: -0.1700

Data Index: 5501787 (Open Web Text)

Max Activating Token Index: 110

Text #10

Max Range: 4.6118. Min Range: -4.6118

Max Act: 4.2859. Min Act: -0.1700

Data Index: 1968038 (Open Web Text)

Max Activating Token Index: 95

Text #11

Max Range: 4.6118. Min Range: -4.6118

Max Act: 4.2919. Min Act: -0.1700

Data Index: 3735565 (Open Web Text)

Max Activating Token Index: 273

Text #12

Max Range: 4.6118. Min Range: -4.6118

Max Act: 4.2691. Min Act: -0.1700

Data Index: 5553847 (Open Web Text)

Max Activating Token Index: 647

Text #13

Max Range: 4.6118. Min Range: -4.6118

Max Act: 4.3002. Min Act: -0.1700

Data Index: 8673196 (Open Web Text)

Max Activating Token Index: 647

Text #14

Max Range: 4.6118. Min Range: -4.6118

Max Act: 4.2636. Min Act: -0.1700

Data Index: 3060241 (Open Web Text)

Max Activating Token Index: 20

Text #15

Max Range: 4.6118. Min Range: -4.6118

Max Act: 4.2793. Min Act: -0.1700

Data Index: 1730127 (Open Web Text)

Max Activating Token Index: 865

Text #16

Max Range: 4.6118. Min Range: -4.6118

Max Act: 4.2576. Min Act: -0.1700

Data Index: 1350973 (Open Web Text)

Max Activating Token Index: 26

Text #17

Max Range: 4.6118. Min Range: -4.6118

Max Act: 4.2585. Min Act: -0.1700

Data Index: 3747333 (Open Web Text)

Max Activating Token Index: 183

Text #18

Max Range: 4.6118. Min Range: -4.6118

Max Act: 4.2485. Min Act: -0.1700

Data Index: 8315453 (Open Web Text)

Max Activating Token Index: 478

Text #19

Max Range: 4.6118. Min Range: -4.6118

Max Act: 4.2907. Min Act: -0.1700

Data Index: 1690498 (Open Web Text)

Max Activating Token Index: 970