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

Dataset: Open Web Text

Neuron 2601 in Layer 0

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: 3.2965. Min Range: -3.2965

Max Act: 3.2965. Min Act: -0.1700

Data Index: 5556244 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 3.2965. Min Range: -3.2965

Max Act: 3.2065. Min Act: -0.1700

Data Index: 3938090 (Open Web Text)

Max Activating Token Index: 8

Text #2

Max Range: 3.2965. Min Range: -3.2965

Max Act: 3.1903. Min Act: -0.1700

Data Index: 2853131 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 3.2965. Min Range: -3.2965

Max Act: 3.1757. Min Act: -0.1700

Data Index: 5528986 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 3.2965. Min Range: -3.2965

Max Act: 3.1756. Min Act: -0.1700

Data Index: 8220012 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 3.2965. Min Range: -3.2965

Max Act: 3.1706. Min Act: -0.1700

Data Index: 130347 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 3.2965. Min Range: -3.2965

Max Act: 3.1553. Min Act: -0.1700

Data Index: 8132706 (Open Web Text)

Max Activating Token Index: 10

Text #7

Max Range: 3.2965. Min Range: -3.2965

Max Act: 3.1499. Min Act: -0.1700

Data Index: 3324547 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 3.2965. Min Range: -3.2965

Max Act: 3.1488. Min Act: -0.1700

Data Index: 2137974 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 3.2965. Min Range: -3.2965

Max Act: 3.1225. Min Act: -0.1700

Data Index: 2037710 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 3.2965. Min Range: -3.2965

Max Act: 3.1449. Min Act: -0.1700

Data Index: 2433630 (Open Web Text)

Max Activating Token Index: 800

Text #11

Max Range: 3.2965. Min Range: -3.2965

Max Act: 3.1225. Min Act: -0.1700

Data Index: 1387927 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 3.2965. Min Range: -3.2965

Max Act: 3.0893. Min Act: -0.1700

Data Index: 130345 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 3.2965. Min Range: -3.2965

Max Act: 3.0946. Min Act: -0.1700

Data Index: 7869654 (Open Web Text)

Max Activating Token Index: 8

Text #14

Max Range: 3.2965. Min Range: -3.2965

Max Act: 3.0791. Min Act: -0.1700

Data Index: 5473822 (Open Web Text)

Max Activating Token Index: 768

Text #15

Max Range: 3.2965. Min Range: -3.2965

Max Act: 3.0784. Min Act: -0.1700

Data Index: 7129815 (Open Web Text)

Max Activating Token Index: 220

Text #16

Max Range: 3.2965. Min Range: -3.2965

Max Act: 3.0745. Min Act: -0.1700

Data Index: 5886501 (Open Web Text)

Max Activating Token Index: 7

Text #17

Max Range: 3.2965. Min Range: -3.2965

Max Act: 3.0661. Min Act: -0.1700

Data Index: 6804854 (Open Web Text)

Max Activating Token Index: 542

Text #18

Max Range: 3.2965. Min Range: -3.2965

Max Act: 3.0620. Min Act: -0.1700

Data Index: 2612503 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 3.2965. Min Range: -3.2965

Max Act: 3.0535. Min Act: -0.1700

Data Index: 543255 (Open Web Text)

Max Activating Token Index: 457