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

Dataset: Open Web Text

Neuron 528 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: 3.8988. Min Range: -3.8988

Max Act: 3.8988. Min Act: -0.1700

Data Index: 1230731 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 3.8988. Min Range: -3.8988

Max Act: 3.8749. Min Act: -0.1700

Data Index: 6135716 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 3.8988. Min Range: -3.8988

Max Act: 3.8853. Min Act: -0.1700

Data Index: 8073582 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 3.8988. Min Range: -3.8988

Max Act: 3.8523. Min Act: -0.1700

Data Index: 1035537 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 3.8988. Min Range: -3.8988

Max Act: 3.8233. Min Act: -0.1700

Data Index: 2240465 (Open Web Text)

Max Activating Token Index: 9

Text #5

Max Range: 3.8988. Min Range: -3.8988

Max Act: 3.8009. Min Act: -0.1700

Data Index: 4402907 (Open Web Text)

Max Activating Token Index: 8

Text #6

Max Range: 3.8988. Min Range: -3.8988

Max Act: 3.8167. Min Act: -0.1700

Data Index: 4694521 (Open Web Text)

Max Activating Token Index: 3

Text #7

Max Range: 3.8988. Min Range: -3.8988

Max Act: 3.8049. Min Act: -0.1700

Data Index: 2024863 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 3.8988. Min Range: -3.8988

Max Act: 3.7709. Min Act: -0.1700

Data Index: 3624900 (Open Web Text)

Max Activating Token Index: 8

Text #9

Max Range: 3.8988. Min Range: -3.8988

Max Act: 3.7814. Min Act: -0.1700

Data Index: 1522232 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 3.8988. Min Range: -3.8988

Max Act: 3.7700. Min Act: -0.1700

Data Index: 4090868 (Open Web Text)

Max Activating Token Index: 7

Text #11

Max Range: 3.8988. Min Range: -3.8988

Max Act: 3.7759. Min Act: -0.1700

Data Index: 7611692 (Open Web Text)

Max Activating Token Index: 22

Text #12

Max Range: 3.8988. Min Range: -3.8988

Max Act: 3.7635. Min Act: -0.1700

Data Index: 3363190 (Open Web Text)

Max Activating Token Index: 25

Text #13

Max Range: 3.8988. Min Range: -3.8988

Max Act: 3.7624. Min Act: -0.1700

Data Index: 1065524 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 3.8988. Min Range: -3.8988

Max Act: 3.7609. Min Act: -0.1700

Data Index: 850124 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 3.8988. Min Range: -3.8988

Max Act: 3.7596. Min Act: -0.1700

Data Index: 4879500 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 3.8988. Min Range: -3.8988

Max Act: 3.7686. Min Act: -0.1700

Data Index: 5180112 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 3.8988. Min Range: -3.8988

Max Act: 3.7422. Min Act: -0.1700

Data Index: 5343673 (Open Web Text)

Max Activating Token Index: 8

Text #18

Max Range: 3.8988. Min Range: -3.8988

Max Act: 3.7504. Min Act: -0.1700

Data Index: 5690476 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 3.8988. Min Range: -3.8988

Max Act: 3.7695. Min Act: -0.1700

Data Index: 3892900 (Open Web Text)

Max Activating Token Index: 5