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

Dataset: Open Web Text

Neuron 1667 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: 4.4708. Min Range: -4.4708

Max Act: 4.4708. Min Act: -0.1700

Data Index: 4477415 (Open Web Text)

Max Activating Token Index: 987

Text #1

Max Range: 4.4708. Min Range: -4.4708

Max Act: 4.3494. Min Act: -0.1700

Data Index: 5777122 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 4.4708. Min Range: -4.4708

Max Act: 4.3652. Min Act: -0.1700

Data Index: 2920471 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 4.4708. Min Range: -4.4708

Max Act: 4.3377. Min Act: -0.1700

Data Index: 4937398 (Open Web Text)

Max Activating Token Index: 45

Text #4

Max Range: 4.4708. Min Range: -4.4708

Max Act: 4.3160. Min Act: -0.1700

Data Index: 3063924 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 4.4708. Min Range: -4.4708

Max Act: 4.3235. Min Act: -0.1700

Data Index: 8561099 (Open Web Text)

Max Activating Token Index: 701

Text #6

Max Range: 4.4708. Min Range: -4.4708

Max Act: 4.2838. Min Act: -0.1700

Data Index: 5199357 (Open Web Text)

Max Activating Token Index: 831

Text #7

Max Range: 4.4708. Min Range: -4.4708

Max Act: 4.2792. Min Act: -0.1700

Data Index: 3870999 (Open Web Text)

Max Activating Token Index: 875

Text #8

Max Range: 4.4708. Min Range: -4.4708

Max Act: 4.2381. Min Act: -0.1700

Data Index: 6023024 (Open Web Text)

Max Activating Token Index: 11

Text #9

Max Range: 4.4708. Min Range: -4.4708

Max Act: 4.2498. Min Act: -0.1700

Data Index: 202864 (Open Web Text)

Max Activating Token Index: 30

Text #10

Max Range: 4.4708. Min Range: -4.4708

Max Act: 4.2499. Min Act: -0.1700

Data Index: 8606626 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 4.4708. Min Range: -4.4708

Max Act: 4.2134. Min Act: -0.1700

Data Index: 434227 (Open Web Text)

Max Activating Token Index: 67

Text #12

Max Range: 4.4708. Min Range: -4.4708

Max Act: 4.2103. Min Act: -0.1700

Data Index: 4005472 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 4.4708. Min Range: -4.4708

Max Act: 4.1908. Min Act: -0.1700

Data Index: 1991401 (Open Web Text)

Max Activating Token Index: 821

Text #14

Max Range: 4.4708. Min Range: -4.4708

Max Act: 4.1938. Min Act: -0.1700

Data Index: 7933792 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 4.4708. Min Range: -4.4708

Max Act: 4.2027. Min Act: -0.1700

Data Index: 5942845 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 4.4708. Min Range: -4.4708

Max Act: 4.2163. Min Act: -0.1700

Data Index: 231963 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 4.4708. Min Range: -4.4708

Max Act: 4.2086. Min Act: -0.1700

Data Index: 4428128 (Open Web Text)

Max Activating Token Index: 1010

Text #18

Max Range: 4.4708. Min Range: -4.4708

Max Act: 4.1784. Min Act: -0.1700

Data Index: 1989443 (Open Web Text)

Max Activating Token Index: 516

Text #19

Max Range: 4.4708. Min Range: -4.4708

Max Act: 4.1781. Min Act: -0.1700

Data Index: 3364705 (Open Web Text)

Max Activating Token Index: 853