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

Dataset: Open Web Text

Neuron 2224 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: 1.9076. Min Range: -1.9076

Max Act: 1.9076. Min Act: -0.1700

Data Index: 3698638 (Open Web Text)

Max Activating Token Index: 35

Text #1

Max Range: 1.9076. Min Range: -1.9076

Max Act: 1.8338. Min Act: -0.1700

Data Index: 6379020 (Open Web Text)

Max Activating Token Index: 239

Text #2

Max Range: 1.9076. Min Range: -1.9076

Max Act: 1.8220. Min Act: -0.1700

Data Index: 7312441 (Open Web Text)

Max Activating Token Index: 30

Text #3

Max Range: 1.9076. Min Range: -1.9076

Max Act: 1.8199. Min Act: -0.1700

Data Index: 466710 (Open Web Text)

Max Activating Token Index: 28

Text #4

Max Range: 1.9076. Min Range: -1.9076

Max Act: 1.8279. Min Act: -0.1700

Data Index: 7316413 (Open Web Text)

Max Activating Token Index: 46

Text #5

Max Range: 1.9076. Min Range: -1.9076

Max Act: 1.8088. Min Act: -0.1700

Data Index: 3500805 (Open Web Text)

Max Activating Token Index: 20

Text #6

Max Range: 1.9076. Min Range: -1.9076

Max Act: 1.8193. Min Act: -0.1700

Data Index: 6734003 (Open Web Text)

Max Activating Token Index: 49

Text #7

Max Range: 1.9076. Min Range: -1.9076

Max Act: 1.8104. Min Act: -0.1700

Data Index: 797563 (Open Web Text)

Max Activating Token Index: 37

Text #8

Max Range: 1.9076. Min Range: -1.9076

Max Act: 1.8024. Min Act: -0.1700

Data Index: 3266118 (Open Web Text)

Max Activating Token Index: 513

Text #9

Max Range: 1.9076. Min Range: -1.9076

Max Act: 1.8088. Min Act: -0.1700

Data Index: 867172 (Open Web Text)

Max Activating Token Index: 73

Text #10

Max Range: 1.9076. Min Range: -1.9076

Max Act: 1.8180. Min Act: -0.1700

Data Index: 7760074 (Open Web Text)

Max Activating Token Index: 63

Text #11

Max Range: 1.9076. Min Range: -1.9076

Max Act: 1.8077. Min Act: -0.1700

Data Index: 4145243 (Open Web Text)

Max Activating Token Index: 32

Text #12

Max Range: 1.9076. Min Range: -1.9076

Max Act: 1.7975. Min Act: -0.1700

Data Index: 26106 (Open Web Text)

Max Activating Token Index: 31

Text #13

Max Range: 1.9076. Min Range: -1.9076

Max Act: 1.8078. Min Act: -0.1700

Data Index: 29537 (Open Web Text)

Max Activating Token Index: 147

Text #14

Max Range: 1.9076. Min Range: -1.9076

Max Act: 1.7972. Min Act: -0.1700

Data Index: 6370200 (Open Web Text)

Max Activating Token Index: 69

Text #15

Max Range: 1.9076. Min Range: -1.9076

Max Act: 1.8058. Min Act: -0.1700

Data Index: 6840287 (Open Web Text)

Max Activating Token Index: 286

Text #16

Max Range: 1.9076. Min Range: -1.9076

Max Act: 1.8012. Min Act: -0.1700

Data Index: 1874829 (Open Web Text)

Max Activating Token Index: 164

Text #17

Max Range: 1.9076. Min Range: -1.9076

Max Act: 1.8121. Min Act: -0.1700

Data Index: 6004125 (Open Web Text)

Max Activating Token Index: 392

Text #18

Max Range: 1.9076. Min Range: -1.9076

Max Act: 1.8045. Min Act: -0.1700

Data Index: 1736822 (Open Web Text)

Max Activating Token Index: 284

Text #19

Max Range: 1.9076. Min Range: -1.9076

Max Act: 1.8018. Min Act: -0.1699

Data Index: 5051826 (Open Web Text)

Max Activating Token Index: 169