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

Dataset: Open Web Text

Neuron 2239 in Layer 0

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: 8.0249. Min Range: -8.0249

Max Act: 7.9904. Min Act: -0.1700

Data Index: 4924253 (Open Web Text)

Max Activating Token Index: 9

Text #1

Max Range: 8.0249. Min Range: -8.0249

Max Act: 8.0094. Min Act: -0.1700

Data Index: 4231361 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 8.0249. Min Range: -8.0249

Max Act: 7.9981. Min Act: -0.1700

Data Index: 2761864 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 8.0249. Min Range: -8.0249

Max Act: 7.9900. Min Act: -0.1700

Data Index: 2235121 (Open Web Text)

Max Activating Token Index: 8

Text #4

Max Range: 8.0249. Min Range: -8.0249

Max Act: 8.0020. Min Act: -0.1700

Data Index: 4218221 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 8.0249. Min Range: -8.0249

Max Act: 7.9972. Min Act: -0.1700

Data Index: 2134820 (Open Web Text)

Max Activating Token Index: 7

Text #6

Max Range: 8.0249. Min Range: -8.0249

Max Act: 7.9972. Min Act: -0.1699

Data Index: 2060848 (Open Web Text)

Max Activating Token Index: 7

Text #7

Max Range: 8.0249. Min Range: -8.0249

Max Act: 7.9775. Min Act: -0.1700

Data Index: 1887874 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 8.0249. Min Range: -8.0249

Max Act: 7.9899. Min Act: -0.1700

Data Index: 7972908 (Open Web Text)

Max Activating Token Index: 10

Text #9

Max Range: 8.0249. Min Range: -8.0249

Max Act: 7.9810. Min Act: -0.1700

Data Index: 5546311 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 8.0249. Min Range: -8.0249

Max Act: 8.0185. Min Act: -0.1698

Data Index: 3625076 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 8.0249. Min Range: -8.0249

Max Act: 8.0214. Min Act: -0.1700

Data Index: 5240272 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 8.0249. Min Range: -8.0249

Max Act: 8.0037. Min Act: -0.1700

Data Index: 3369978 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 8.0249. Min Range: -8.0249

Max Act: 8.0249. Min Act: -0.1700

Data Index: 4651175 (Open Web Text)

Max Activating Token Index: 12

Text #14

Max Range: 8.0249. Min Range: -8.0249

Max Act: 7.9380. Min Act: -0.1700

Data Index: 1011707 (Open Web Text)

Max Activating Token Index: 25

Text #15

Max Range: 8.0249. Min Range: -8.0249

Max Act: 7.9262. Min Act: -0.1700

Data Index: 4409927 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 8.0249. Min Range: -8.0249

Max Act: 7.9215. Min Act: -0.1700

Data Index: 4539353 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 8.0249. Min Range: -8.0249

Max Act: 7.9240. Min Act: -0.1700

Data Index: 229368 (Open Web Text)

Max Activating Token Index: 24

Text #18

Max Range: 8.0249. Min Range: -8.0249

Max Act: 7.9496. Min Act: -0.1700

Data Index: 1163138 (Open Web Text)

Max Activating Token Index: 22

Text #19

Max Range: 8.0249. Min Range: -8.0249

Max Act: 7.9291. Min Act: -0.1700

Data Index: 2960737 (Open Web Text)

Max Activating Token Index: 6