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

Dataset: Open Web Text

Neuron 1815 in Layer 5

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: 4.8999. Min Range: -4.8999

Max Act: 4.8999. Min Act: -0.1700

Data Index: 916551 (Open Web Text)

Max Activating Token Index: 224

Text #1

Max Range: 4.8999. Min Range: -4.8999

Max Act: 4.7979. Min Act: -0.1700

Data Index: 4806541 (Open Web Text)

Max Activating Token Index: 46

Text #2

Max Range: 4.8999. Min Range: -4.8999

Max Act: 4.7485. Min Act: -0.1700

Data Index: 8352653 (Open Web Text)

Max Activating Token Index: 342

Text #3

Max Range: 4.8999. Min Range: -4.8999

Max Act: 4.7418. Min Act: -0.1700

Data Index: 478411 (Open Web Text)

Max Activating Token Index: 72

Text #4

Max Range: 4.8999. Min Range: -4.8999

Max Act: 4.7307. Min Act: -0.1700

Data Index: 1694248 (Open Web Text)

Max Activating Token Index: 617

Text #5

Max Range: 4.8999. Min Range: -4.8999

Max Act: 4.7458. Min Act: -0.1700

Data Index: 1034947 (Open Web Text)

Max Activating Token Index: 1012

Text #6

Max Range: 4.8999. Min Range: -4.8999

Max Act: 4.7482. Min Act: -0.1700

Data Index: 5568181 (Open Web Text)

Max Activating Token Index: 64

Text #7

Max Range: 4.8999. Min Range: -4.8999

Max Act: 4.7256. Min Act: -0.1700

Data Index: 1792458 (Open Web Text)

Max Activating Token Index: 639

Text #8

Max Range: 4.8999. Min Range: -4.8999

Max Act: 4.7134. Min Act: -0.1700

Data Index: 6530581 (Open Web Text)

Max Activating Token Index: 228

Text #9

Max Range: 4.8999. Min Range: -4.8999

Max Act: 4.6691. Min Act: -0.1700

Data Index: 4610215 (Open Web Text)

Max Activating Token Index: 763

Text #10

Max Range: 4.8999. Min Range: -4.8999

Max Act: 4.6487. Min Act: -0.1700

Data Index: 6790799 (Open Web Text)

Max Activating Token Index: 853

Text #11

Max Range: 4.8999. Min Range: -4.8999

Max Act: 4.6538. Min Act: -0.1700

Data Index: 2396827 (Open Web Text)

Max Activating Token Index: 720

Text #12

Max Range: 4.8999. Min Range: -4.8999

Max Act: 4.6562. Min Act: -0.1700

Data Index: 8323558 (Open Web Text)

Max Activating Token Index: 677

Text #13

Max Range: 4.8999. Min Range: -4.8999

Max Act: 4.6382. Min Act: -0.1700

Data Index: 7221933 (Open Web Text)

Max Activating Token Index: 669

Text #14

Max Range: 4.8999. Min Range: -4.8999

Max Act: 4.6204. Min Act: -0.1700

Data Index: 8245067 (Open Web Text)

Max Activating Token Index: 988

Text #15

Max Range: 4.8999. Min Range: -4.8999

Max Act: 4.6382. Min Act: -0.1700

Data Index: 2055258 (Open Web Text)

Max Activating Token Index: 281

Text #16

Max Range: 4.8999. Min Range: -4.8999

Max Act: 4.6438. Min Act: -0.1700

Data Index: 1510571 (Open Web Text)

Max Activating Token Index: 336

Text #17

Max Range: 4.8999. Min Range: -4.8999

Max Act: 4.6405. Min Act: -0.1700

Data Index: 2170133 (Open Web Text)

Max Activating Token Index: 248

Text #18

Max Range: 4.8999. Min Range: -4.8999

Max Act: 4.6590. Min Act: -0.1700

Data Index: 6480566 (Open Web Text)

Max Activating Token Index: 645

Text #19

Max Range: 4.8999. Min Range: -4.8999

Max Act: 4.6657. Min Act: -0.1700

Data Index: 3535978 (Open Web Text)

Max Activating Token Index: 331