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

Dataset: Open Web Text

Neuron 2470 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: 2.9028. Min Range: -2.9028

Max Act: 2.9028. Min Act: -0.1700

Data Index: 2885446 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 2.9028. Min Range: -2.9028

Max Act: 2.9009. Min Act: -0.1700

Data Index: 7845584 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 2.9028. Min Range: -2.9028

Max Act: 2.8861. Min Act: -0.1700

Data Index: 1597719 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 2.9028. Min Range: -2.9028

Max Act: 2.8831. Min Act: -0.1700

Data Index: 6301182 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 2.9028. Min Range: -2.9028

Max Act: 2.8641. Min Act: -0.1700

Data Index: 8501741 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 2.9028. Min Range: -2.9028

Max Act: 2.8538. Min Act: -0.1700

Data Index: 4748906 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 2.9028. Min Range: -2.9028

Max Act: 2.8416. Min Act: -0.1700

Data Index: 6926858 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 2.9028. Min Range: -2.9028

Max Act: 2.8416. Min Act: -0.1700

Data Index: 6818601 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 2.9028. Min Range: -2.9028

Max Act: 2.8525. Min Act: -0.1700

Data Index: 8085826 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 2.9028. Min Range: -2.9028

Max Act: 2.8479. Min Act: -0.1700

Data Index: 4698121 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 2.9028. Min Range: -2.9028

Max Act: 2.8416. Min Act: -0.1700

Data Index: 7080443 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 2.9028. Min Range: -2.9028

Max Act: 2.8416. Min Act: -0.1700

Data Index: 8517031 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 2.9028. Min Range: -2.9028

Max Act: 2.8191. Min Act: -0.1700

Data Index: 6300528 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 2.9028. Min Range: -2.9028

Max Act: 2.8265. Min Act: -0.1700

Data Index: 8243161 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 2.9028. Min Range: -2.9028

Max Act: 2.8285. Min Act: -0.1700

Data Index: 7066407 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 2.9028. Min Range: -2.9028

Max Act: 2.8132. Min Act: -0.1700

Data Index: 2229288 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 2.9028. Min Range: -2.9028

Max Act: 2.8088. Min Act: -0.1700

Data Index: 5583981 (Open Web Text)

Max Activating Token Index: 8

Text #17

Max Range: 2.9028. Min Range: -2.9028

Max Act: 2.8091. Min Act: -0.1700

Data Index: 3542889 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 2.9028. Min Range: -2.9028

Max Act: 2.8139. Min Act: -0.1700

Data Index: 8227740 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 2.9028. Min Range: -2.9028

Max Act: 2.8061. Min Act: -0.1700

Data Index: 951750 (Open Web Text)

Max Activating Token Index: 5