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

Dataset: Open Web Text

Neuron 1339 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: 4.7071. Min Range: -4.7071

Max Act: 4.6884. Min Act: -0.1700

Data Index: 8269046 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 4.7071. Min Range: -4.7071

Max Act: 4.7071. Min Act: -0.1700

Data Index: 4633181 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 4.7071. Min Range: -4.7071

Max Act: 4.6836. Min Act: -0.1700

Data Index: 4110048 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 4.7071. Min Range: -4.7071

Max Act: 4.6784. Min Act: -0.1700

Data Index: 1708399 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 4.7071. Min Range: -4.7071

Max Act: 4.6394. Min Act: -0.1700

Data Index: 3793233 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 4.7071. Min Range: -4.7071

Max Act: 4.6218. Min Act: -0.1700

Data Index: 170851 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 4.7071. Min Range: -4.7071

Max Act: 4.6255. Min Act: -0.1700

Data Index: 6788398 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 4.7071. Min Range: -4.7071

Max Act: 4.6232. Min Act: -0.1700

Data Index: 5805388 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 4.7071. Min Range: -4.7071

Max Act: 4.5812. Min Act: -0.1700

Data Index: 6232046 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 4.7071. Min Range: -4.7071

Max Act: 4.5779. Min Act: -0.1700

Data Index: 1350654 (Open Web Text)

Max Activating Token Index: 8

Text #10

Max Range: 4.7071. Min Range: -4.7071

Max Act: 4.5839. Min Act: -0.1700

Data Index: 4489968 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 4.7071. Min Range: -4.7071

Max Act: 4.5824. Min Act: -0.1700

Data Index: 2945181 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 4.7071. Min Range: -4.7071

Max Act: 4.5848. Min Act: -0.1700

Data Index: 6363843 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 4.7071. Min Range: -4.7071

Max Act: 4.5487. Min Act: -0.1700

Data Index: 968755 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 4.7071. Min Range: -4.7071

Max Act: 4.5131. Min Act: -0.1700

Data Index: 3367064 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 4.7071. Min Range: -4.7071

Max Act: 4.5149. Min Act: -0.1700

Data Index: 6908191 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 4.7071. Min Range: -4.7071

Max Act: 4.4788. Min Act: -0.1700

Data Index: 4402238 (Open Web Text)

Max Activating Token Index: 8

Text #17

Max Range: 4.7071. Min Range: -4.7071

Max Act: 4.5024. Min Act: -0.1700

Data Index: 6710958 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 4.7071. Min Range: -4.7071

Max Act: 4.4922. Min Act: -0.1700

Data Index: 4779064 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 4.7071. Min Range: -4.7071

Max Act: 4.4904. Min Act: -0.1700

Data Index: 3846331 (Open Web Text)

Max Activating Token Index: 4