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

Dataset: Open Web Text

Neuron 722 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: 3.7185. Min Range: -3.7185

Max Act: 3.7098. Min Act: -0.1700

Data Index: 6234970 (Open Web Text)

Max Activating Token Index: 53

Text #1

Max Range: 3.7185. Min Range: -3.7185

Max Act: 3.7185. Min Act: -0.1700

Data Index: 6298609 (Open Web Text)

Max Activating Token Index: 539

Text #2

Max Range: 3.7185. Min Range: -3.7185

Max Act: 3.6754. Min Act: -0.1700

Data Index: 8375586 (Open Web Text)

Max Activating Token Index: 402

Text #3

Max Range: 3.7185. Min Range: -3.7185

Max Act: 3.6852. Min Act: -0.1700

Data Index: 786062 (Open Web Text)

Max Activating Token Index: 161

Text #4

Max Range: 3.7185. Min Range: -3.7185

Max Act: 3.6480. Min Act: -0.1700

Data Index: 7498760 (Open Web Text)

Max Activating Token Index: 522

Text #5

Max Range: 3.7185. Min Range: -3.7185

Max Act: 3.6346. Min Act: -0.1700

Data Index: 729972 (Open Web Text)

Max Activating Token Index: 236

Text #6

Max Range: 3.7185. Min Range: -3.7185

Max Act: 3.6256. Min Act: -0.1700

Data Index: 2649466 (Open Web Text)

Max Activating Token Index: 922

Text #7

Max Range: 3.7185. Min Range: -3.7185

Max Act: 3.6075. Min Act: -0.1700

Data Index: 8729664 (Open Web Text)

Max Activating Token Index: 476

Text #8

Max Range: 3.7185. Min Range: -3.7185

Max Act: 3.6304. Min Act: -0.1700

Data Index: 438504 (Open Web Text)

Max Activating Token Index: 242

Text #9

Max Range: 3.7185. Min Range: -3.7185

Max Act: 3.6382. Min Act: -0.1700

Data Index: 8432905 (Open Web Text)

Max Activating Token Index: 778

Text #10

Max Range: 3.7185. Min Range: -3.7185

Max Act: 3.6026. Min Act: -0.1700

Data Index: 4121088 (Open Web Text)

Max Activating Token Index: 943

Text #11

Max Range: 3.7185. Min Range: -3.7185

Max Act: 3.6269. Min Act: -0.1700

Data Index: 7557307 (Open Web Text)

Max Activating Token Index: 577

Text #12

Max Range: 3.7185. Min Range: -3.7185

Max Act: 3.5865. Min Act: -0.1700

Data Index: 6588810 (Open Web Text)

Max Activating Token Index: 804

Text #13

Max Range: 3.7185. Min Range: -3.7185

Max Act: 3.6135. Min Act: -0.1700

Data Index: 4410420 (Open Web Text)

Max Activating Token Index: 324

Text #14

Max Range: 3.7185. Min Range: -3.7185

Max Act: 3.5980. Min Act: -0.1700

Data Index: 7036844 (Open Web Text)

Max Activating Token Index: 729

Text #15

Max Range: 3.7185. Min Range: -3.7185

Max Act: 3.6037. Min Act: -0.1700

Data Index: 83438 (Open Web Text)

Max Activating Token Index: 462

Text #16

Max Range: 3.7185. Min Range: -3.7185

Max Act: 3.5729. Min Act: -0.1700

Data Index: 3174551 (Open Web Text)

Max Activating Token Index: 87

Text #17

Max Range: 3.7185. Min Range: -3.7185

Max Act: 3.5629. Min Act: -0.1700

Data Index: 729079 (Open Web Text)

Max Activating Token Index: 369

Text #18

Max Range: 3.7185. Min Range: -3.7185

Max Act: 3.5692. Min Act: -0.1700

Data Index: 852423 (Open Web Text)

Max Activating Token Index: 50

Text #19

Max Range: 3.7185. Min Range: -3.7185

Max Act: 3.5855. Min Act: -0.1700

Data Index: 7192788 (Open Web Text)

Max Activating Token Index: 128