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

Dataset: Open Web Text

Neuron 1167 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: 3.4151. Min Range: -3.4151

Max Act: 3.4151. Min Act: -0.1700

Data Index: 5408937 (Open Web Text)

Max Activating Token Index: 24

Text #1

Max Range: 3.4151. Min Range: -3.4151

Max Act: 3.4034. Min Act: -0.1700

Data Index: 2748905 (Open Web Text)

Max Activating Token Index: 829

Text #2

Max Range: 3.4151. Min Range: -3.4151

Max Act: 3.3977. Min Act: -0.1700

Data Index: 3584229 (Open Web Text)

Max Activating Token Index: 22

Text #3

Max Range: 3.4151. Min Range: -3.4151

Max Act: 3.3675. Min Act: -0.1700

Data Index: 1017378 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 3.4151. Min Range: -3.4151

Max Act: 3.3649. Min Act: -0.1700

Data Index: 7734399 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 3.4151. Min Range: -3.4151

Max Act: 3.3408. Min Act: -0.1700

Data Index: 3340339 (Open Web Text)

Max Activating Token Index: 826

Text #6

Max Range: 3.4151. Min Range: -3.4151

Max Act: 3.3511. Min Act: -0.1700

Data Index: 3931416 (Open Web Text)

Max Activating Token Index: 7

Text #7

Max Range: 3.4151. Min Range: -3.4151

Max Act: 3.3063. Min Act: -0.1700

Data Index: 2144000 (Open Web Text)

Max Activating Token Index: 865

Text #8

Max Range: 3.4151. Min Range: -3.4151

Max Act: 3.3020. Min Act: -0.1700

Data Index: 6738096 (Open Web Text)

Max Activating Token Index: 8

Text #9

Max Range: 3.4151. Min Range: -3.4151

Max Act: 3.2628. Min Act: -0.1700

Data Index: 4181806 (Open Web Text)

Max Activating Token Index: 8

Text #10

Max Range: 3.4151. Min Range: -3.4151

Max Act: 3.2835. Min Act: -0.1700

Data Index: 295959 (Open Web Text)

Max Activating Token Index: 25

Text #11

Max Range: 3.4151. Min Range: -3.4151

Max Act: 3.2750. Min Act: -0.1700

Data Index: 7763577 (Open Web Text)

Max Activating Token Index: 861

Text #12

Max Range: 3.4151. Min Range: -3.4151

Max Act: 3.2949. Min Act: -0.1700

Data Index: 2003076 (Open Web Text)

Max Activating Token Index: 948

Text #13

Max Range: 3.4151. Min Range: -3.4151

Max Act: 3.2925. Min Act: -0.1700

Data Index: 7518586 (Open Web Text)

Max Activating Token Index: 26

Text #14

Max Range: 3.4151. Min Range: -3.4151

Max Act: 3.2727. Min Act: -0.1700

Data Index: 6669896 (Open Web Text)

Max Activating Token Index: 255

Text #15

Max Range: 3.4151. Min Range: -3.4151

Max Act: 3.2795. Min Act: -0.1700

Data Index: 5634934 (Open Web Text)

Max Activating Token Index: 827

Text #16

Max Range: 3.4151. Min Range: -3.4151

Max Act: 3.2672. Min Act: -0.1700

Data Index: 5594913 (Open Web Text)

Max Activating Token Index: 11

Text #17

Max Range: 3.4151. Min Range: -3.4151

Max Act: 3.2700. Min Act: -0.1700

Data Index: 4823374 (Open Web Text)

Max Activating Token Index: 806

Text #18

Max Range: 3.4151. Min Range: -3.4151

Max Act: 3.2802. Min Act: -0.1700

Data Index: 4275552 (Open Web Text)

Max Activating Token Index: 12

Text #19

Max Range: 3.4151. Min Range: -3.4151

Max Act: 3.2529. Min Act: -0.1700

Data Index: 4083786 (Open Web Text)

Max Activating Token Index: 889