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

Dataset: Open Web Text

Neuron 838 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: 3.1404. Min Range: -3.1404

Max Act: 3.1404. Min Act: -0.1700

Data Index: 7313151 (Open Web Text)

Max Activating Token Index: 8

Text #1

Max Range: 3.1404. Min Range: -3.1404

Max Act: 3.1248. Min Act: -0.1700

Data Index: 5626042 (Open Web Text)

Max Activating Token Index: 7

Text #2

Max Range: 3.1404. Min Range: -3.1404

Max Act: 3.1274. Min Act: -0.1700

Data Index: 6651577 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 3.1404. Min Range: -3.1404

Max Act: 3.0969. Min Act: -0.1700

Data Index: 6574041 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 3.1404. Min Range: -3.1404

Max Act: 3.0138. Min Act: -0.1700

Data Index: 2878492 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 3.1404. Min Range: -3.1404

Max Act: 2.9927. Min Act: -0.1700

Data Index: 8229534 (Open Web Text)

Max Activating Token Index: 7

Text #6

Max Range: 3.1404. Min Range: -3.1404

Max Act: 2.9842. Min Act: -0.1700

Data Index: 7934912 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 3.1404. Min Range: -3.1404

Max Act: 2.9824. Min Act: -0.1700

Data Index: 5872518 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 3.1404. Min Range: -3.1404

Max Act: 2.9853. Min Act: -0.1700

Data Index: 5759808 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 3.1404. Min Range: -3.1404

Max Act: 2.9775. Min Act: -0.1700

Data Index: 3312902 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 3.1404. Min Range: -3.1404

Max Act: 2.9612. Min Act: -0.1700

Data Index: 2772277 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 3.1404. Min Range: -3.1404

Max Act: 2.9731. Min Act: -0.1700

Data Index: 6999647 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 3.1404. Min Range: -3.1404

Max Act: 2.9792. Min Act: -0.1700

Data Index: 6687198 (Open Web Text)

Max Activating Token Index: 7

Text #13

Max Range: 3.1404. Min Range: -3.1404

Max Act: 2.9624. Min Act: -0.1700

Data Index: 7588135 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 3.1404. Min Range: -3.1404

Max Act: 2.9442. Min Act: -0.1700

Data Index: 2392106 (Open Web Text)

Max Activating Token Index: 8

Text #15

Max Range: 3.1404. Min Range: -3.1404

Max Act: 2.9463. Min Act: -0.1700

Data Index: 6372583 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 3.1404. Min Range: -3.1404

Max Act: 2.9462. Min Act: -0.1700

Data Index: 342102 (Open Web Text)

Max Activating Token Index: 7

Text #17

Max Range: 3.1404. Min Range: -3.1404

Max Act: 2.9465. Min Act: -0.1700

Data Index: 1372216 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 3.1404. Min Range: -3.1404

Max Act: 2.9375. Min Act: -0.1700

Data Index: 6983071 (Open Web Text)

Max Activating Token Index: 7

Text #19

Max Range: 3.1404. Min Range: -3.1404

Max Act: 2.9431. Min Act: -0.1700

Data Index: 5457555 (Open Web Text)

Max Activating Token Index: 4