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

Dataset: Open Web Text

Neuron 748 in Layer 2

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: 4.1867. Min Range: -4.1867

Max Act: 4.1867. Min Act: -0.1700

Data Index: 7487807 (Open Web Text)

Max Activating Token Index: 56

Text #1

Max Range: 4.1867. Min Range: -4.1867

Max Act: 4.1504. Min Act: -0.1700

Data Index: 4811831 (Open Web Text)

Max Activating Token Index: 39

Text #2

Max Range: 4.1867. Min Range: -4.1867

Max Act: 4.1326. Min Act: -0.1700

Data Index: 4811830 (Open Web Text)

Max Activating Token Index: 59

Text #3

Max Range: 4.1867. Min Range: -4.1867

Max Act: 4.1189. Min Act: -0.1700

Data Index: 4811859 (Open Web Text)

Max Activating Token Index: 46

Text #4

Max Range: 4.1867. Min Range: -4.1867

Max Act: 4.0799. Min Act: -0.1700

Data Index: 10219 (Open Web Text)

Max Activating Token Index: 27

Text #5

Max Range: 4.1867. Min Range: -4.1867

Max Act: 4.0756. Min Act: -0.1700

Data Index: 7487805 (Open Web Text)

Max Activating Token Index: 164

Text #6

Max Range: 4.1867. Min Range: -4.1867

Max Act: 4.0560. Min Act: -0.1700

Data Index: 4811857 (Open Web Text)

Max Activating Token Index: 179

Text #7

Max Range: 4.1867. Min Range: -4.1867

Max Act: 4.0635. Min Act: -0.1700

Data Index: 4811858 (Open Web Text)

Max Activating Token Index: 66

Text #8

Max Range: 4.1867. Min Range: -4.1867

Max Act: 4.0669. Min Act: -0.1700

Data Index: 2910249 (Open Web Text)

Max Activating Token Index: 94

Text #9

Max Range: 4.1867. Min Range: -4.1867

Max Act: 4.0681. Min Act: -0.1700

Data Index: 4811832 (Open Web Text)

Max Activating Token Index: 93

Text #10

Max Range: 4.1867. Min Range: -4.1867

Max Act: 4.0400. Min Act: -0.1700

Data Index: 3401978 (Open Web Text)

Max Activating Token Index: 41

Text #11

Max Range: 4.1867. Min Range: -4.1867

Max Act: 4.0248. Min Act: -0.1700

Data Index: 3401944 (Open Web Text)

Max Activating Token Index: 65

Text #12

Max Range: 4.1867. Min Range: -4.1867

Max Act: 4.0024. Min Act: -0.1700

Data Index: 3401946 (Open Web Text)

Max Activating Token Index: 35

Text #13

Max Range: 4.1867. Min Range: -4.1867

Max Act: 4.0117. Min Act: -0.1700

Data Index: 4811860 (Open Web Text)

Max Activating Token Index: 100

Text #14

Max Range: 4.1867. Min Range: -4.1867

Max Act: 4.0280. Min Act: -0.1700

Data Index: 4811829 (Open Web Text)

Max Activating Token Index: 172

Text #15

Max Range: 4.1867. Min Range: -4.1867

Max Act: 4.0119. Min Act: -0.1700

Data Index: 3401945 (Open Web Text)

Max Activating Token Index: 90

Text #16

Max Range: 4.1867. Min Range: -4.1867

Max Act: 3.9808. Min Act: -0.1700

Data Index: 3401971 (Open Web Text)

Max Activating Token Index: 151

Text #17

Max Range: 4.1867. Min Range: -4.1867

Max Act: 3.9800. Min Act: -0.1700

Data Index: 3401941 (Open Web Text)

Max Activating Token Index: 69

Text #18

Max Range: 4.1867. Min Range: -4.1867

Max Act: 3.9683. Min Act: -0.1700

Data Index: 3401942 (Open Web Text)

Max Activating Token Index: 133

Text #19

Max Range: 4.1867. Min Range: -4.1867

Max Act: 3.9653. Min Act: -0.1700

Data Index: 3401973 (Open Web Text)

Max Activating Token Index: 179