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

Dataset: Open Web Text

Neuron 1636 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: 4.4741. Min Range: -4.4741

Max Act: 4.4741. Min Act: -0.1700

Data Index: 3918301 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 4.4741. Min Range: -4.4741

Max Act: 4.4701. Min Act: -0.1700

Data Index: 5478767 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 4.4741. Min Range: -4.4741

Max Act: 4.4270. Min Act: -0.1700

Data Index: 1319884 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 4.4741. Min Range: -4.4741

Max Act: 4.3928. Min Act: -0.1700

Data Index: 1219919 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 4.4741. Min Range: -4.4741

Max Act: 4.4005. Min Act: -0.1700

Data Index: 7686150 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 4.4741. Min Range: -4.4741

Max Act: 4.4059. Min Act: -0.1700

Data Index: 6127639 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 4.4741. Min Range: -4.4741

Max Act: 4.3602. Min Act: -0.1700

Data Index: 5367048 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 4.4741. Min Range: -4.4741

Max Act: 4.3777. Min Act: -0.1700

Data Index: 903110 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 4.4741. Min Range: -4.4741

Max Act: 4.3818. Min Act: -0.1700

Data Index: 8477305 (Open Web Text)

Max Activating Token Index: 9

Text #9

Max Range: 4.4741. Min Range: -4.4741

Max Act: 4.3687. Min Act: -0.1700

Data Index: 3252454 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 4.4741. Min Range: -4.4741

Max Act: 4.3777. Min Act: -0.1700

Data Index: 5633776 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 4.4741. Min Range: -4.4741

Max Act: 4.3617. Min Act: -0.1700

Data Index: 867207 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 4.4741. Min Range: -4.4741

Max Act: 4.3715. Min Act: -0.1700

Data Index: 3045523 (Open Web Text)

Max Activating Token Index: 10

Text #13

Max Range: 4.4741. Min Range: -4.4741

Max Act: 4.3795. Min Act: -0.1700

Data Index: 6595383 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 4.4741. Min Range: -4.4741

Max Act: 4.3837. Min Act: -0.1700

Data Index: 2701646 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 4.4741. Min Range: -4.4741

Max Act: 4.3881. Min Act: -0.1700

Data Index: 6484181 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 4.4741. Min Range: -4.4741

Max Act: 4.3722. Min Act: -0.1700

Data Index: 1965052 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 4.4741. Min Range: -4.4741

Max Act: 4.3860. Min Act: -0.1700

Data Index: 6259906 (Open Web Text)

Max Activating Token Index: 7

Text #18

Max Range: 4.4741. Min Range: -4.4741

Max Act: 4.3613. Min Act: -0.1700

Data Index: 2262942 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 4.4741. Min Range: -4.4741

Max Act: 4.3630. Min Act: -0.1700

Data Index: 1612836 (Open Web Text)

Max Activating Token Index: 6