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

Dataset: Open Web Text

Neuron 996 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: 4.5229. Min Range: -4.5229

Max Act: 4.4994. Min Act: -0.1700

Data Index: 2509890 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 4.5229. Min Range: -4.5229

Max Act: 4.5015. Min Act: -0.1700

Data Index: 4955824 (Open Web Text)

Max Activating Token Index: 14

Text #2

Max Range: 4.5229. Min Range: -4.5229

Max Act: 4.5141. Min Act: -0.1700

Data Index: 7603186 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 4.5229. Min Range: -4.5229

Max Act: 4.5150. Min Act: -0.1700

Data Index: 642182 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 4.5229. Min Range: -4.5229

Max Act: 4.5020. Min Act: -0.1700

Data Index: 7809325 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 4.5229. Min Range: -4.5229

Max Act: 4.5229. Min Act: -0.1700

Data Index: 8061998 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 4.5229. Min Range: -4.5229

Max Act: 4.4853. Min Act: -0.1700

Data Index: 33387 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 4.5229. Min Range: -4.5229

Max Act: 4.4853. Min Act: -0.1700

Data Index: 1319711 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 4.5229. Min Range: -4.5229

Max Act: 4.4678. Min Act: -0.1700

Data Index: 8595006 (Open Web Text)

Max Activating Token Index: 8

Text #9

Max Range: 4.5229. Min Range: -4.5229

Max Act: 4.4853. Min Act: -0.1700

Data Index: 8075010 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 4.5229. Min Range: -4.5229

Max Act: 4.4679. Min Act: -0.1700

Data Index: 700202 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 4.5229. Min Range: -4.5229

Max Act: 4.4853. Min Act: -0.1700

Data Index: 1252789 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 4.5229. Min Range: -4.5229

Max Act: 4.4853. Min Act: -0.1700

Data Index: 4812248 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 4.5229. Min Range: -4.5229

Max Act: 4.4806. Min Act: -0.1700

Data Index: 7861569 (Open Web Text)

Max Activating Token Index: 936

Text #14

Max Range: 4.5229. Min Range: -4.5229

Max Act: 4.4714. Min Act: -0.1700

Data Index: 6538851 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 4.5229. Min Range: -4.5229

Max Act: 4.4589. Min Act: -0.1700

Data Index: 898240 (Open Web Text)

Max Activating Token Index: 10

Text #16

Max Range: 4.5229. Min Range: -4.5229

Max Act: 4.4778. Min Act: -0.1700

Data Index: 7690428 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 4.5229. Min Range: -4.5229

Max Act: 4.4853. Min Act: -0.1700

Data Index: 613473 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 4.5229. Min Range: -4.5229

Max Act: 4.4853. Min Act: -0.1700

Data Index: 7269082 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 4.5229. Min Range: -4.5229

Max Act: 4.4852. Min Act: -0.1700

Data Index: 6828561 (Open Web Text)

Max Activating Token Index: 9