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

Dataset: Open Web Text

Neuron 908 in Layer 2

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: 4.2912. Min Range: -4.2912

Max Act: 4.2710. Min Act: -0.1700

Data Index: 6561822 (Open Web Text)

Max Activating Token Index: 888

Text #1

Max Range: 4.2912. Min Range: -4.2912

Max Act: 4.2912. Min Act: -0.1700

Data Index: 4204930 (Open Web Text)

Max Activating Token Index: 464

Text #2

Max Range: 4.2912. Min Range: -4.2912

Max Act: 4.2255. Min Act: -0.1700

Data Index: 6844904 (Open Web Text)

Max Activating Token Index: 517

Text #3

Max Range: 4.2912. Min Range: -4.2912

Max Act: 4.1932. Min Act: -0.1700

Data Index: 3276650 (Open Web Text)

Max Activating Token Index: 561

Text #4

Max Range: 4.2912. Min Range: -4.2912

Max Act: 4.1774. Min Act: -0.1700

Data Index: 7421689 (Open Web Text)

Max Activating Token Index: 925

Text #5

Max Range: 4.2912. Min Range: -4.2912

Max Act: 4.1717. Min Act: -0.1700

Data Index: 5005949 (Open Web Text)

Max Activating Token Index: 531

Text #6

Max Range: 4.2912. Min Range: -4.2912

Max Act: 4.1753. Min Act: -0.1700

Data Index: 5537362 (Open Web Text)

Max Activating Token Index: 609

Text #7

Max Range: 4.2912. Min Range: -4.2912

Max Act: 4.1569. Min Act: -0.1700

Data Index: 2119336 (Open Web Text)

Max Activating Token Index: 751

Text #8

Max Range: 4.2912. Min Range: -4.2912

Max Act: 4.1840. Min Act: -0.1700

Data Index: 4128525 (Open Web Text)

Max Activating Token Index: 994

Text #9

Max Range: 4.2912. Min Range: -4.2912

Max Act: 4.0957. Min Act: -0.1700

Data Index: 2821086 (Open Web Text)

Max Activating Token Index: 983

Text #10

Max Range: 4.2912. Min Range: -4.2912

Max Act: 4.1488. Min Act: -0.1700

Data Index: 5372031 (Open Web Text)

Max Activating Token Index: 648

Text #11

Max Range: 4.2912. Min Range: -4.2912

Max Act: 4.1472. Min Act: -0.1700

Data Index: 5412020 (Open Web Text)

Max Activating Token Index: 999

Text #12

Max Range: 4.2912. Min Range: -4.2912

Max Act: 4.0910. Min Act: -0.1700

Data Index: 2512223 (Open Web Text)

Max Activating Token Index: 884

Text #13

Max Range: 4.2912. Min Range: -4.2912

Max Act: 4.1439. Min Act: -0.1700

Data Index: 3091162 (Open Web Text)

Max Activating Token Index: 335

Text #14

Max Range: 4.2912. Min Range: -4.2912

Max Act: 4.0885. Min Act: -0.1678

Data Index: 4281498 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 4.2912. Min Range: -4.2912

Max Act: 4.0859. Min Act: -0.1700

Data Index: 1924481 (Open Web Text)

Max Activating Token Index: 480

Text #16

Max Range: 4.2912. Min Range: -4.2912

Max Act: 4.0888. Min Act: -0.1700

Data Index: 3937283 (Open Web Text)

Max Activating Token Index: 88

Text #17

Max Range: 4.2912. Min Range: -4.2912

Max Act: 4.1113. Min Act: -0.1700

Data Index: 654342 (Open Web Text)

Max Activating Token Index: 513

Text #18

Max Range: 4.2912. Min Range: -4.2912

Max Act: 4.1019. Min Act: -0.1700

Data Index: 5142453 (Open Web Text)

Max Activating Token Index: 443

Text #19

Max Range: 4.2912. Min Range: -4.2912

Max Act: 4.1253. Min Act: -0.1700

Data Index: 785000 (Open Web Text)

Max Activating Token Index: 402