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

Dataset: Open Web Text

Neuron 2753 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: 4.6754. Min Range: -4.6754

Max Act: 4.6754. Min Act: -0.1700

Data Index: 2227564 (Open Web Text)

Max Activating Token Index: 84

Text #1

Max Range: 4.6754. Min Range: -4.6754

Max Act: 4.5374. Min Act: -0.1700

Data Index: 5825534 (Open Web Text)

Max Activating Token Index: 82

Text #2

Max Range: 4.6754. Min Range: -4.6754

Max Act: 4.5515. Min Act: -0.1700

Data Index: 4989029 (Open Web Text)

Max Activating Token Index: 33

Text #3

Max Range: 4.6754. Min Range: -4.6754

Max Act: 4.5369. Min Act: -0.1700

Data Index: 623122 (Open Web Text)

Max Activating Token Index: 13

Text #4

Max Range: 4.6754. Min Range: -4.6754

Max Act: 4.5051. Min Act: -0.1700

Data Index: 2891481 (Open Web Text)

Max Activating Token Index: 14

Text #5

Max Range: 4.6754. Min Range: -4.6754

Max Act: 4.5052. Min Act: -0.1700

Data Index: 129705 (Open Web Text)

Max Activating Token Index: 292

Text #6

Max Range: 4.6754. Min Range: -4.6754

Max Act: 4.4733. Min Act: -0.1700

Data Index: 6973943 (Open Web Text)

Max Activating Token Index: 540

Text #7

Max Range: 4.6754. Min Range: -4.6754

Max Act: 4.4425. Min Act: -0.1700

Data Index: 8689593 (Open Web Text)

Max Activating Token Index: 25

Text #8

Max Range: 4.6754. Min Range: -4.6754

Max Act: 4.4316. Min Act: -0.1700

Data Index: 5889162 (Open Web Text)

Max Activating Token Index: 314

Text #9

Max Range: 4.6754. Min Range: -4.6754

Max Act: 4.3861. Min Act: -0.1700

Data Index: 6060921 (Open Web Text)

Max Activating Token Index: 419

Text #10

Max Range: 4.6754. Min Range: -4.6754

Max Act: 4.3854. Min Act: -0.1700

Data Index: 8707346 (Open Web Text)

Max Activating Token Index: 62

Text #11

Max Range: 4.6754. Min Range: -4.6754

Max Act: 4.3739. Min Act: -0.1700

Data Index: 6952727 (Open Web Text)

Max Activating Token Index: 48

Text #12

Max Range: 4.6754. Min Range: -4.6754

Max Act: 4.3652. Min Act: -0.1700

Data Index: 4567430 (Open Web Text)

Max Activating Token Index: 590

Text #13

Max Range: 4.6754. Min Range: -4.6754

Max Act: 4.3898. Min Act: -0.1700

Data Index: 2760139 (Open Web Text)

Max Activating Token Index: 153

Text #14

Max Range: 4.6754. Min Range: -4.6754

Max Act: 4.3881. Min Act: -0.1700

Data Index: 771610 (Open Web Text)

Max Activating Token Index: 8

Text #15

Max Range: 4.6754. Min Range: -4.6754

Max Act: 4.3629. Min Act: -0.1700

Data Index: 3527450 (Open Web Text)

Max Activating Token Index: 18

Text #16

Max Range: 4.6754. Min Range: -4.6754

Max Act: 4.3605. Min Act: -0.1700

Data Index: 3732345 (Open Web Text)

Max Activating Token Index: 22

Text #17

Max Range: 4.6754. Min Range: -4.6754

Max Act: 4.3751. Min Act: -0.1700

Data Index: 4197114 (Open Web Text)

Max Activating Token Index: 55

Text #18

Max Range: 4.6754. Min Range: -4.6754

Max Act: 4.3811. Min Act: -0.1700

Data Index: 4888486 (Open Web Text)

Max Activating Token Index: 745

Text #19

Max Range: 4.6754. Min Range: -4.6754

Max Act: 4.3545. Min Act: -0.1700

Data Index: 7899584 (Open Web Text)

Max Activating Token Index: 11