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

Dataset: Open Web Text

Neuron 899 in Layer 1

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: 2.0848. Min Range: -2.0848

Max Act: 2.0848. Min Act: -0.1700

Data Index: 7310574 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 2.0848. Min Range: -2.0848

Max Act: 2.0465. Min Act: -0.1699

Data Index: 6783434 (Open Web Text)

Max Activating Token Index: 94

Text #2

Max Range: 2.0848. Min Range: -2.0848

Max Act: 2.0271. Min Act: -0.1700

Data Index: 5506915 (Open Web Text)

Max Activating Token Index: 212

Text #3

Max Range: 2.0848. Min Range: -2.0848

Max Act: 2.0313. Min Act: -0.1700

Data Index: 384338 (Open Web Text)

Max Activating Token Index: 62

Text #4

Max Range: 2.0848. Min Range: -2.0848

Max Act: 2.0336. Min Act: -0.1700

Data Index: 6772927 (Open Web Text)

Max Activating Token Index: 79

Text #5

Max Range: 2.0848. Min Range: -2.0848

Max Act: 2.0202. Min Act: -0.1699

Data Index: 5344721 (Open Web Text)

Max Activating Token Index: 9

Text #6

Max Range: 2.0848. Min Range: -2.0848

Max Act: 2.0134. Min Act: -0.1700

Data Index: 4684580 (Open Web Text)

Max Activating Token Index: 9

Text #7

Max Range: 2.0848. Min Range: -2.0848

Max Act: 2.0120. Min Act: -0.1700

Data Index: 925555 (Open Web Text)

Max Activating Token Index: 99

Text #8

Max Range: 2.0848. Min Range: -2.0848

Max Act: 2.0138. Min Act: -0.1700

Data Index: 6544467 (Open Web Text)

Max Activating Token Index: 165

Text #9

Max Range: 2.0848. Min Range: -2.0848

Max Act: 2.0118. Min Act: -0.1699

Data Index: 7621898 (Open Web Text)

Max Activating Token Index: 655

Text #10

Max Range: 2.0848. Min Range: -2.0848

Max Act: 1.9923. Min Act: -0.1700

Data Index: 7256824 (Open Web Text)

Max Activating Token Index: 13

Text #11

Max Range: 2.0848. Min Range: -2.0848

Max Act: 2.0081. Min Act: -0.1700

Data Index: 50241 (Open Web Text)

Max Activating Token Index: 612

Text #12

Max Range: 2.0848. Min Range: -2.0848

Max Act: 2.0040. Min Act: -0.1700

Data Index: 3418569 (Open Web Text)

Max Activating Token Index: 151

Text #13

Max Range: 2.0848. Min Range: -2.0848

Max Act: 2.0016. Min Act: -0.1700

Data Index: 6623881 (Open Web Text)

Max Activating Token Index: 41

Text #14

Max Range: 2.0848. Min Range: -2.0848

Max Act: 1.9973. Min Act: -0.1700

Data Index: 6421531 (Open Web Text)

Max Activating Token Index: 14

Text #15

Max Range: 2.0848. Min Range: -2.0848

Max Act: 1.9967. Min Act: -0.1700

Data Index: 5600876 (Open Web Text)

Max Activating Token Index: 103

Text #16

Max Range: 2.0848. Min Range: -2.0848

Max Act: 1.9840. Min Act: -0.1700

Data Index: 1177434 (Open Web Text)

Max Activating Token Index: 124

Text #17

Max Range: 2.0848. Min Range: -2.0848

Max Act: 1.9901. Min Act: -0.1700

Data Index: 3740398 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 2.0848. Min Range: -2.0848

Max Act: 1.9939. Min Act: -0.1700

Data Index: 2455184 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 2.0848. Min Range: -2.0848

Max Act: 1.9779. Min Act: -0.1700

Data Index: 1569283 (Open Web Text)

Max Activating Token Index: 10