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

Dataset: Open Web Text

Neuron 1518 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: 2.7087. Min Range: -2.7087

Max Act: 2.7087. Min Act: -0.1700

Data Index: 7704587 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 2.7087. Min Range: -2.7087

Max Act: 2.6627. Min Act: -0.1700

Data Index: 5239542 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 2.7087. Min Range: -2.7087

Max Act: 2.6627. Min Act: -0.1700

Data Index: 8244276 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 2.7087. Min Range: -2.7087

Max Act: 2.6631. Min Act: -0.1700

Data Index: 5734760 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 2.7087. Min Range: -2.7087

Max Act: 2.6661. Min Act: -0.1700

Data Index: 3712676 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 2.7087. Min Range: -2.7087

Max Act: 2.6539. Min Act: -0.1700

Data Index: 2002957 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 2.7087. Min Range: -2.7087

Max Act: 2.6396. Min Act: -0.1700

Data Index: 6903239 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 2.7087. Min Range: -2.7087

Max Act: 2.6378. Min Act: -0.1700

Data Index: 3418253 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 2.7087. Min Range: -2.7087

Max Act: 2.6433. Min Act: -0.1700

Data Index: 4496818 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 2.7087. Min Range: -2.7087

Max Act: 2.6416. Min Act: -0.1700

Data Index: 5322612 (Open Web Text)

Max Activating Token Index: 409

Text #10

Max Range: 2.7087. Min Range: -2.7087

Max Act: 2.6141. Min Act: -0.1700

Data Index: 6167761 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 2.7087. Min Range: -2.7087

Max Act: 2.6116. Min Act: -0.1700

Data Index: 1721511 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 2.7087. Min Range: -2.7087

Max Act: 2.6084. Min Act: -0.1700

Data Index: 2735440 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 2.7087. Min Range: -2.7087

Max Act: 2.6216. Min Act: -0.1700

Data Index: 4466490 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 2.7087. Min Range: -2.7087

Max Act: 2.6084. Min Act: -0.1700

Data Index: 3612309 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 2.7087. Min Range: -2.7087

Max Act: 2.6074. Min Act: -0.1700

Data Index: 6701518 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 2.7087. Min Range: -2.7087

Max Act: 2.6179. Min Act: -0.1700

Data Index: 2474749 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 2.7087. Min Range: -2.7087

Max Act: 2.6084. Min Act: -0.1700

Data Index: 2942320 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 2.7087. Min Range: -2.7087

Max Act: 2.6113. Min Act: -0.1700

Data Index: 3172330 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 2.7087. Min Range: -2.7087

Max Act: 2.6124. Min Act: -0.1700

Data Index: 3258734 (Open Web Text)

Max Activating Token Index: 7