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

Dataset: Open Web Text

Neuron 2449 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: 3.9066. Min Range: -3.9066

Max Act: 3.9066. Min Act: -0.1700

Data Index: 1399447 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 3.9066. Min Range: -3.9066

Max Act: 3.8448. Min Act: -0.1700

Data Index: 102913 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 3.9066. Min Range: -3.9066

Max Act: 3.8410. Min Act: -0.1700

Data Index: 7037401 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 3.9066. Min Range: -3.9066

Max Act: 3.7779. Min Act: -0.1700

Data Index: 991142 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 3.9066. Min Range: -3.9066

Max Act: 3.7527. Min Act: -0.1700

Data Index: 3194458 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 3.9066. Min Range: -3.9066

Max Act: 3.7330. Min Act: -0.1700

Data Index: 1887941 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 3.9066. Min Range: -3.9066

Max Act: 3.6982. Min Act: -0.1700

Data Index: 1756503 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 3.9066. Min Range: -3.9066

Max Act: 3.6982. Min Act: -0.1700

Data Index: 5661362 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 3.9066. Min Range: -3.9066

Max Act: 3.6913. Min Act: -0.1700

Data Index: 8405480 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 3.9066. Min Range: -3.9066

Max Act: 3.6982. Min Act: -0.1700

Data Index: 2113579 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 3.9066. Min Range: -3.9066

Max Act: 3.6840. Min Act: -0.1700

Data Index: 3066732 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 3.9066. Min Range: -3.9066

Max Act: 3.6326. Min Act: -0.1700

Data Index: 2360049 (Open Web Text)

Max Activating Token Index: 11

Text #12

Max Range: 3.9066. Min Range: -3.9066

Max Act: 3.6444. Min Act: -0.1700

Data Index: 6688517 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 3.9066. Min Range: -3.9066

Max Act: 3.6562. Min Act: -0.1700

Data Index: 7101835 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 3.9066. Min Range: -3.9066

Max Act: 3.6223. Min Act: -0.1700

Data Index: 4637023 (Open Web Text)

Max Activating Token Index: 15

Text #15

Max Range: 3.9066. Min Range: -3.9066

Max Act: 3.6261. Min Act: -0.1700

Data Index: 5414149 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 3.9066. Min Range: -3.9066

Max Act: 3.5922. Min Act: -0.1700

Data Index: 5615025 (Open Web Text)

Max Activating Token Index: 8

Text #17

Max Range: 3.9066. Min Range: -3.9066

Max Act: 3.6032. Min Act: -0.1700

Data Index: 6268679 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 3.9066. Min Range: -3.9066

Max Act: 3.5847. Min Act: -0.1700

Data Index: 7529736 (Open Web Text)

Max Activating Token Index: 10

Text #19

Max Range: 3.9066. Min Range: -3.9066

Max Act: 3.5846. Min Act: -0.1700

Data Index: 4723137 (Open Web Text)

Max Activating Token Index: 10