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

Dataset: Open Web Text

Neuron 308 in Layer 2

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: 3.9572. Min Range: -3.9572

Max Act: 3.9572. Min Act: -0.1700

Data Index: 5858654 (Open Web Text)

Max Activating Token Index: 894

Text #1

Max Range: 3.9572. Min Range: -3.9572

Max Act: 3.8064. Min Act: -0.1700

Data Index: 256486 (Open Web Text)

Max Activating Token Index: 16

Text #2

Max Range: 3.9572. Min Range: -3.9572

Max Act: 3.8208. Min Act: -0.1700

Data Index: 8295132 (Open Web Text)

Max Activating Token Index: 9

Text #3

Max Range: 3.9572. Min Range: -3.9572

Max Act: 3.8467. Min Act: -0.1700

Data Index: 5763966 (Open Web Text)

Max Activating Token Index: 14

Text #4

Max Range: 3.9572. Min Range: -3.9572

Max Act: 3.7928. Min Act: -0.1700

Data Index: 1540859 (Open Web Text)

Max Activating Token Index: 524

Text #5

Max Range: 3.9572. Min Range: -3.9572

Max Act: 3.7724. Min Act: -0.1700

Data Index: 2670900 (Open Web Text)

Max Activating Token Index: 10

Text #6

Max Range: 3.9572. Min Range: -3.9572

Max Act: 3.7197. Min Act: -0.1696

Data Index: 3367674 (Open Web Text)

Max Activating Token Index: 434

Text #7

Max Range: 3.9572. Min Range: -3.9572

Max Act: 3.7268. Min Act: -0.1700

Data Index: 8572844 (Open Web Text)

Max Activating Token Index: 204

Text #8

Max Range: 3.9572. Min Range: -3.9572

Max Act: 3.6873. Min Act: -0.1700

Data Index: 4595172 (Open Web Text)

Max Activating Token Index: 84

Text #9

Max Range: 3.9572. Min Range: -3.9572

Max Act: 3.6888. Min Act: -0.1700

Data Index: 1762260 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 3.9572. Min Range: -3.9572

Max Act: 3.6812. Min Act: -0.1700

Data Index: 3490837 (Open Web Text)

Max Activating Token Index: 17

Text #11

Max Range: 3.9572. Min Range: -3.9572

Max Act: 3.6860. Min Act: -0.1700

Data Index: 7923633 (Open Web Text)

Max Activating Token Index: 9

Text #12

Max Range: 3.9572. Min Range: -3.9572

Max Act: 3.6706. Min Act: -0.1700

Data Index: 4840835 (Open Web Text)

Max Activating Token Index: 11

Text #13

Max Range: 3.9572. Min Range: -3.9572

Max Act: 3.6525. Min Act: -0.1700

Data Index: 2632405 (Open Web Text)

Max Activating Token Index: 12

Text #14

Max Range: 3.9572. Min Range: -3.9572

Max Act: 3.6302. Min Act: -0.1700

Data Index: 3683123 (Open Web Text)

Max Activating Token Index: 7

Text #15

Max Range: 3.9572. Min Range: -3.9572

Max Act: 3.6274. Min Act: -0.1700

Data Index: 4209035 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 3.9572. Min Range: -3.9572

Max Act: 3.6379. Min Act: -0.1700

Data Index: 1540860 (Open Web Text)

Max Activating Token Index: 217

Text #17

Max Range: 3.9572. Min Range: -3.9572

Max Act: 3.6381. Min Act: -0.1700

Data Index: 3402417 (Open Web Text)

Max Activating Token Index: 48

Text #18

Max Range: 3.9572. Min Range: -3.9572

Max Act: 3.6234. Min Act: -0.1700

Data Index: 8232287 (Open Web Text)

Max Activating Token Index: 17

Text #19

Max Range: 3.9572. Min Range: -3.9572

Max Act: 3.6361. Min Act: -0.1700

Data Index: 6606591 (Open Web Text)

Max Activating Token Index: 18