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

Dataset: Open Web Text

Neuron 1042 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: 5.4272. Min Range: -5.4272

Max Act: 5.4272. Min Act: -0.1700

Data Index: 5256222 (Open Web Text)

Max Activating Token Index: 925

Text #1

Max Range: 5.4272. Min Range: -5.4272

Max Act: 5.2268. Min Act: -0.1700

Data Index: 244809 (Open Web Text)

Max Activating Token Index: 377

Text #2

Max Range: 5.4272. Min Range: -5.4272

Max Act: 5.1938. Min Act: -0.1700

Data Index: 2988026 (Open Web Text)

Max Activating Token Index: 858

Text #3

Max Range: 5.4272. Min Range: -5.4272

Max Act: 5.1580. Min Act: -0.1700

Data Index: 938102 (Open Web Text)

Max Activating Token Index: 461

Text #4

Max Range: 5.4272. Min Range: -5.4272

Max Act: 5.1557. Min Act: -0.1700

Data Index: 2331918 (Open Web Text)

Max Activating Token Index: 276

Text #5

Max Range: 5.4272. Min Range: -5.4272

Max Act: 5.1533. Min Act: -0.1700

Data Index: 2904210 (Open Web Text)

Max Activating Token Index: 376

Text #6

Max Range: 5.4272. Min Range: -5.4272

Max Act: 5.1239. Min Act: -0.1700

Data Index: 2160471 (Open Web Text)

Max Activating Token Index: 520

Text #7

Max Range: 5.4272. Min Range: -5.4272

Max Act: 5.1172. Min Act: -0.1700

Data Index: 7307934 (Open Web Text)

Max Activating Token Index: 381

Text #8

Max Range: 5.4272. Min Range: -5.4272

Max Act: 5.1223. Min Act: -0.1700

Data Index: 5829692 (Open Web Text)

Max Activating Token Index: 38

Text #9

Max Range: 5.4272. Min Range: -5.4272

Max Act: 5.1098. Min Act: -0.1700

Data Index: 7725302 (Open Web Text)

Max Activating Token Index: 144

Text #10

Max Range: 5.4272. Min Range: -5.4272

Max Act: 5.1380. Min Act: -0.1700

Data Index: 4483345 (Open Web Text)

Max Activating Token Index: 688

Text #11

Max Range: 5.4272. Min Range: -5.4272

Max Act: 5.0995. Min Act: -0.1700

Data Index: 7013175 (Open Web Text)

Max Activating Token Index: 18

Text #12

Max Range: 5.4272. Min Range: -5.4272

Max Act: 5.0901. Min Act: -0.1700

Data Index: 3004202 (Open Web Text)

Max Activating Token Index: 443

Text #13

Max Range: 5.4272. Min Range: -5.4272

Max Act: 5.0935. Min Act: -0.1700

Data Index: 2465857 (Open Web Text)

Max Activating Token Index: 29

Text #14

Max Range: 5.4272. Min Range: -5.4272

Max Act: 5.0811. Min Act: -0.1700

Data Index: 1683713 (Open Web Text)

Max Activating Token Index: 28

Text #15

Max Range: 5.4272. Min Range: -5.4272

Max Act: 5.0916. Min Act: -0.1700

Data Index: 7486773 (Open Web Text)

Max Activating Token Index: 478

Text #16

Max Range: 5.4272. Min Range: -5.4272

Max Act: 5.0668. Min Act: -0.1700

Data Index: 3601255 (Open Web Text)

Max Activating Token Index: 86

Text #17

Max Range: 5.4272. Min Range: -5.4272

Max Act: 5.0902. Min Act: -0.1700

Data Index: 3568123 (Open Web Text)

Max Activating Token Index: 21

Text #18

Max Range: 5.4272. Min Range: -5.4272

Max Act: 5.0503. Min Act: -0.1700

Data Index: 784800 (Open Web Text)

Max Activating Token Index: 30

Text #19

Max Range: 5.4272. Min Range: -5.4272

Max Act: 5.0825. Min Act: -0.1700

Data Index: 6544491 (Open Web Text)

Max Activating Token Index: 49