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

Dataset: Open Web Text

Neuron 1416 in Layer 3

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: 3.2454. Min Range: -3.2454

Max Act: 3.2454. Min Act: -0.1700

Data Index: 8041155 (Open Web Text)

Max Activating Token Index: 922

Text #1

Max Range: 3.2454. Min Range: -3.2454

Max Act: 3.2142. Min Act: -0.1700

Data Index: 3360391 (Open Web Text)

Max Activating Token Index: 21

Text #2

Max Range: 3.2454. Min Range: -3.2454

Max Act: 3.2047. Min Act: -0.1700

Data Index: 6550673 (Open Web Text)

Max Activating Token Index: 428

Text #3

Max Range: 3.2454. Min Range: -3.2454

Max Act: 3.1949. Min Act: -0.1700

Data Index: 2714901 (Open Web Text)

Max Activating Token Index: 193

Text #4

Max Range: 3.2454. Min Range: -3.2454

Max Act: 3.2095. Min Act: -0.1700

Data Index: 7111065 (Open Web Text)

Max Activating Token Index: 839

Text #5

Max Range: 3.2454. Min Range: -3.2454

Max Act: 3.1818. Min Act: -0.1700

Data Index: 7666910 (Open Web Text)

Max Activating Token Index: 209

Text #6

Max Range: 3.2454. Min Range: -3.2454

Max Act: 3.1837. Min Act: -0.1700

Data Index: 1729642 (Open Web Text)

Max Activating Token Index: 474

Text #7

Max Range: 3.2454. Min Range: -3.2454

Max Act: 3.1838. Min Act: -0.1700

Data Index: 5746632 (Open Web Text)

Max Activating Token Index: 695

Text #8

Max Range: 3.2454. Min Range: -3.2454

Max Act: 3.2076. Min Act: -0.1700

Data Index: 5879503 (Open Web Text)

Max Activating Token Index: 400

Text #9

Max Range: 3.2454. Min Range: -3.2454

Max Act: 3.1084. Min Act: -0.1700

Data Index: 3644058 (Open Web Text)

Max Activating Token Index: 367

Text #10

Max Range: 3.2454. Min Range: -3.2454

Max Act: 3.1214. Min Act: -0.1700

Data Index: 8290096 (Open Web Text)

Max Activating Token Index: 449

Text #11

Max Range: 3.2454. Min Range: -3.2454

Max Act: 3.1284. Min Act: -0.1700

Data Index: 7086507 (Open Web Text)

Max Activating Token Index: 729

Text #12

Max Range: 3.2454. Min Range: -3.2454

Max Act: 3.1152. Min Act: -0.1700

Data Index: 4105985 (Open Web Text)

Max Activating Token Index: 600

Text #13

Max Range: 3.2454. Min Range: -3.2454

Max Act: 3.1328. Min Act: -0.1700

Data Index: 6330331 (Open Web Text)

Max Activating Token Index: 720

Text #14

Max Range: 3.2454. Min Range: -3.2454

Max Act: 3.1111. Min Act: -0.1700

Data Index: 10820 (Open Web Text)

Max Activating Token Index: 564

Text #15

Max Range: 3.2454. Min Range: -3.2454

Max Act: 3.0912. Min Act: -0.1700

Data Index: 8491391 (Open Web Text)

Max Activating Token Index: 672

Text #16

Max Range: 3.2454. Min Range: -3.2454

Max Act: 3.0969. Min Act: -0.1700

Data Index: 6330332 (Open Web Text)

Max Activating Token Index: 172

Text #17

Max Range: 3.2454. Min Range: -3.2454

Max Act: 3.0634. Min Act: -0.1700

Data Index: 6412372 (Open Web Text)

Max Activating Token Index: 754

Text #18

Max Range: 3.2454. Min Range: -3.2454

Max Act: 3.1100. Min Act: -0.1700

Data Index: 2685933 (Open Web Text)

Max Activating Token Index: 945

Text #19

Max Range: 3.2454. Min Range: -3.2454

Max Act: 3.0979. Min Act: -0.1700

Data Index: 5183068 (Open Web Text)

Max Activating Token Index: 710