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

Dataset: Open Web Text

Neuron 2894 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: 3.2727. Min Range: -3.2727

Max Act: 3.2727. Min Act: -0.1700

Data Index: 4440307 (Open Web Text)

Max Activating Token Index: 9

Text #1

Max Range: 3.2727. Min Range: -3.2727

Max Act: 3.2381. Min Act: -0.1700

Data Index: 5619853 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 3.2727. Min Range: -3.2727

Max Act: 3.2414. Min Act: -0.1700

Data Index: 8501574 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 3.2727. Min Range: -3.2727

Max Act: 3.2338. Min Act: -0.1700

Data Index: 2838293 (Open Web Text)

Max Activating Token Index: 743

Text #4

Max Range: 3.2727. Min Range: -3.2727

Max Act: 3.2256. Min Act: -0.1700

Data Index: 238152 (Open Web Text)

Max Activating Token Index: 16

Text #5

Max Range: 3.2727. Min Range: -3.2727

Max Act: 3.2278. Min Act: -0.1700

Data Index: 2169293 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 3.2727. Min Range: -3.2727

Max Act: 3.2375. Min Act: -0.1700

Data Index: 6733822 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 3.2727. Min Range: -3.2727

Max Act: 3.2229. Min Act: -0.1700

Data Index: 4395389 (Open Web Text)

Max Activating Token Index: 16

Text #8

Max Range: 3.2727. Min Range: -3.2727

Max Act: 3.2088. Min Act: -0.1700

Data Index: 3214943 (Open Web Text)

Max Activating Token Index: 9

Text #9

Max Range: 3.2727. Min Range: -3.2727

Max Act: 3.2078. Min Act: -0.1700

Data Index: 3303354 (Open Web Text)

Max Activating Token Index: 7

Text #10

Max Range: 3.2727. Min Range: -3.2727

Max Act: 3.2157. Min Act: -0.1700

Data Index: 7060038 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 3.2727. Min Range: -3.2727

Max Act: 3.1999. Min Act: -0.1700

Data Index: 8566579 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 3.2727. Min Range: -3.2727

Max Act: 3.1942. Min Act: -0.1700

Data Index: 7756857 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 3.2727. Min Range: -3.2727

Max Act: 3.1983. Min Act: -0.1700

Data Index: 4533688 (Open Web Text)

Max Activating Token Index: 29

Text #14

Max Range: 3.2727. Min Range: -3.2727

Max Act: 3.1993. Min Act: -0.1700

Data Index: 4513844 (Open Web Text)

Max Activating Token Index: 773

Text #15

Max Range: 3.2727. Min Range: -3.2727

Max Act: 3.1972. Min Act: -0.1700

Data Index: 7110140 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 3.2727. Min Range: -3.2727

Max Act: 3.1948. Min Act: -0.1700

Data Index: 6000844 (Open Web Text)

Max Activating Token Index: 52

Text #17

Max Range: 3.2727. Min Range: -3.2727

Max Act: 3.1917. Min Act: -0.1700

Data Index: 5662891 (Open Web Text)

Max Activating Token Index: 18

Text #18

Max Range: 3.2727. Min Range: -3.2727

Max Act: 3.1988. Min Act: -0.1700

Data Index: 3052439 (Open Web Text)

Max Activating Token Index: 8

Text #19

Max Range: 3.2727. Min Range: -3.2727

Max Act: 3.1953. Min Act: -0.1700

Data Index: 1807168 (Open Web Text)

Max Activating Token Index: 5