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

Dataset: Open Web Text

Neuron 2280 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: 4.7737. Min Range: -4.7737

Max Act: 4.7737. Min Act: -0.1700

Data Index: 5511158 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 4.7737. Min Range: -4.7737

Max Act: 4.7326. Min Act: -0.1700

Data Index: 6517181 (Open Web Text)

Max Activating Token Index: 7

Text #2

Max Range: 4.7737. Min Range: -4.7737

Max Act: 4.7230. Min Act: -0.1700

Data Index: 1005783 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 4.7737. Min Range: -4.7737

Max Act: 4.6518. Min Act: -0.1700

Data Index: 3775458 (Open Web Text)

Max Activating Token Index: 7

Text #4

Max Range: 4.7737. Min Range: -4.7737

Max Act: 4.6480. Min Act: -0.1700

Data Index: 7121831 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 4.7737. Min Range: -4.7737

Max Act: 4.6331. Min Act: -0.1700

Data Index: 1083421 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 4.7737. Min Range: -4.7737

Max Act: 4.6322. Min Act: -0.1700

Data Index: 7450984 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 4.7737. Min Range: -4.7737

Max Act: 4.6331. Min Act: -0.1700

Data Index: 319965 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 4.7737. Min Range: -4.7737

Max Act: 4.5857. Min Act: -0.1700

Data Index: 5816562 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 4.7737. Min Range: -4.7737

Max Act: 4.5874. Min Act: -0.1700

Data Index: 5401434 (Open Web Text)

Max Activating Token Index: 10

Text #10

Max Range: 4.7737. Min Range: -4.7737

Max Act: 4.6019. Min Act: -0.1700

Data Index: 7528967 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 4.7737. Min Range: -4.7737

Max Act: 4.5990. Min Act: -0.1700

Data Index: 4805332 (Open Web Text)

Max Activating Token Index: 8

Text #12

Max Range: 4.7737. Min Range: -4.7737

Max Act: 4.5922. Min Act: -0.1700

Data Index: 7105797 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 4.7737. Min Range: -4.7737

Max Act: 4.6009. Min Act: -0.1700

Data Index: 3192241 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 4.7737. Min Range: -4.7737

Max Act: 4.5954. Min Act: -0.1700

Data Index: 8677351 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 4.7737. Min Range: -4.7737

Max Act: 4.5738. Min Act: -0.1700

Data Index: 6782648 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 4.7737. Min Range: -4.7737

Max Act: 4.5745. Min Act: -0.1700

Data Index: 1537752 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 4.7737. Min Range: -4.7737

Max Act: 4.5756. Min Act: -0.1700

Data Index: 1066782 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 4.7737. Min Range: -4.7737

Max Act: 4.5710. Min Act: -0.1700

Data Index: 3467034 (Open Web Text)

Max Activating Token Index: 8

Text #19

Max Range: 4.7737. Min Range: -4.7737

Max Act: 4.5735. Min Act: -0.1700

Data Index: 1153973 (Open Web Text)

Max Activating Token Index: 4