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

Dataset: Open Web Text

Neuron 1015 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: 4.1217. Min Range: -4.1217

Max Act: 4.1055. Min Act: -0.1700

Data Index: 1269775 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 4.1217. Min Range: -4.1217

Max Act: 4.1055. Min Act: -0.1700

Data Index: 2276100 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 4.1217. Min Range: -4.1217

Max Act: 4.1217. Min Act: -0.1700

Data Index: 7747931 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 4.1217. Min Range: -4.1217

Max Act: 4.1015. Min Act: -0.1700

Data Index: 5004751 (Open Web Text)

Max Activating Token Index: 2

Text #4

Max Range: 4.1217. Min Range: -4.1217

Max Act: 4.1015. Min Act: -0.1700

Data Index: 7207907 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 4.1217. Min Range: -4.1217

Max Act: 4.0628. Min Act: -0.1700

Data Index: 8534803 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 4.1217. Min Range: -4.1217

Max Act: 4.0912. Min Act: -0.1700

Data Index: 4850533 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 4.1217. Min Range: -4.1217

Max Act: 4.0075. Min Act: -0.1700

Data Index: 3355311 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 4.1217. Min Range: -4.1217

Max Act: 4.0035. Min Act: -0.1700

Data Index: 6847805 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 4.1217. Min Range: -4.1217

Max Act: 4.0266. Min Act: -0.1700

Data Index: 6273651 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 4.1217. Min Range: -4.1217

Max Act: 4.0060. Min Act: -0.1700

Data Index: 7469467 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 4.1217. Min Range: -4.1217

Max Act: 4.0008. Min Act: -0.1700

Data Index: 7081750 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 4.1217. Min Range: -4.1217

Max Act: 4.0066. Min Act: -0.1700

Data Index: 3829233 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 4.1217. Min Range: -4.1217

Max Act: 4.0051. Min Act: -0.1700

Data Index: 7593551 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 4.1217. Min Range: -4.1217

Max Act: 4.0261. Min Act: -0.1700

Data Index: 4179618 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 4.1217. Min Range: -4.1217

Max Act: 4.0076. Min Act: -0.1700

Data Index: 1339122 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 4.1217. Min Range: -4.1217

Max Act: 4.0133. Min Act: -0.1700

Data Index: 7916339 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 4.1217. Min Range: -4.1217

Max Act: 3.9863. Min Act: -0.1700

Data Index: 2622687 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 4.1217. Min Range: -4.1217

Max Act: 3.9839. Min Act: -0.1700

Data Index: 7472069 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 4.1217. Min Range: -4.1217

Max Act: 3.9729. Min Act: -0.1700

Data Index: 2427195 (Open Web Text)

Max Activating Token Index: 6