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

Dataset: Open Web Text

Neuron 1270 in Layer 4

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: 3.5722. Min Range: -3.5722

Max Act: 3.5722. Min Act: -0.1700

Data Index: 3650845 (Open Web Text)

Max Activating Token Index: 806

Text #1

Max Range: 3.5722. Min Range: -3.5722

Max Act: 3.3974. Min Act: -0.1700

Data Index: 3273081 (Open Web Text)

Max Activating Token Index: 997

Text #2

Max Range: 3.5722. Min Range: -3.5722

Max Act: 3.3454. Min Act: -0.1700

Data Index: 5869665 (Open Web Text)

Max Activating Token Index: 830

Text #3

Max Range: 3.5722. Min Range: -3.5722

Max Act: 3.3101. Min Act: -0.1700

Data Index: 7101062 (Open Web Text)

Max Activating Token Index: 636

Text #4

Max Range: 3.5722. Min Range: -3.5722

Max Act: 3.2139. Min Act: -0.1700

Data Index: 7382662 (Open Web Text)

Max Activating Token Index: 784

Text #5

Max Range: 3.5722. Min Range: -3.5722

Max Act: 3.2389. Min Act: -0.1700

Data Index: 3735921 (Open Web Text)

Max Activating Token Index: 500

Text #6

Max Range: 3.5722. Min Range: -3.5722

Max Act: 3.2141. Min Act: -0.1700

Data Index: 1241012 (Open Web Text)

Max Activating Token Index: 944

Text #7

Max Range: 3.5722. Min Range: -3.5722

Max Act: 3.1891. Min Act: -0.1700

Data Index: 1754538 (Open Web Text)

Max Activating Token Index: 949

Text #8

Max Range: 3.5722. Min Range: -3.5722

Max Act: 3.2039. Min Act: -0.1700

Data Index: 5077336 (Open Web Text)

Max Activating Token Index: 764

Text #9

Max Range: 3.5722. Min Range: -3.5722

Max Act: 3.1894. Min Act: -0.1700

Data Index: 6641381 (Open Web Text)

Max Activating Token Index: 240

Text #10

Max Range: 3.5722. Min Range: -3.5722

Max Act: 3.1867. Min Act: -0.1700

Data Index: 6963391 (Open Web Text)

Max Activating Token Index: 351

Text #11

Max Range: 3.5722. Min Range: -3.5722

Max Act: 3.1491. Min Act: -0.1700

Data Index: 8298020 (Open Web Text)

Max Activating Token Index: 195

Text #12

Max Range: 3.5722. Min Range: -3.5722

Max Act: 3.1331. Min Act: -0.1700

Data Index: 8389895 (Open Web Text)

Max Activating Token Index: 110

Text #13

Max Range: 3.5722. Min Range: -3.5722

Max Act: 3.1453. Min Act: -0.1700

Data Index: 789432 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 3.5722. Min Range: -3.5722

Max Act: 3.1088. Min Act: -0.1700

Data Index: 1131512 (Open Web Text)

Max Activating Token Index: 547

Text #15

Max Range: 3.5722. Min Range: -3.5722

Max Act: 3.1066. Min Act: -0.1700

Data Index: 421000 (Open Web Text)

Max Activating Token Index: 183

Text #16

Max Range: 3.5722. Min Range: -3.5722

Max Act: 3.1256. Min Act: -0.1700

Data Index: 4391477 (Open Web Text)

Max Activating Token Index: 922

Text #17

Max Range: 3.5722. Min Range: -3.5722

Max Act: 3.1173. Min Act: -0.1700

Data Index: 4982094 (Open Web Text)

Max Activating Token Index: 1015

Text #18

Max Range: 3.5722. Min Range: -3.5722

Max Act: 3.1215. Min Act: -0.1700

Data Index: 393064 (Open Web Text)

Max Activating Token Index: 637

Text #19

Max Range: 3.5722. Min Range: -3.5722

Max Act: 3.0968. Min Act: -0.1700

Data Index: 634879 (Open Web Text)

Max Activating Token Index: 663