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

Dataset: Open Web Text

Neuron 1408 in Layer 6

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: 6.3790. Min Range: -6.3790

Max Act: 6.3790. Min Act: -0.1700

Data Index: 1548256 (Open Web Text)

Max Activating Token Index: 169

Text #1

Max Range: 6.3790. Min Range: -6.3790

Max Act: 5.9643. Min Act: -0.1700

Data Index: 4652000 (Open Web Text)

Max Activating Token Index: 149

Text #2

Max Range: 6.3790. Min Range: -6.3790

Max Act: 5.8946. Min Act: -0.1700

Data Index: 7451310 (Open Web Text)

Max Activating Token Index: 848

Text #3

Max Range: 6.3790. Min Range: -6.3790

Max Act: 5.8432. Min Act: -0.1700

Data Index: 3562977 (Open Web Text)

Max Activating Token Index: 373

Text #4

Max Range: 6.3790. Min Range: -6.3790

Max Act: 5.7872. Min Act: -0.1700

Data Index: 7903255 (Open Web Text)

Max Activating Token Index: 146

Text #5

Max Range: 6.3790. Min Range: -6.3790

Max Act: 5.6915. Min Act: -0.1700

Data Index: 7994899 (Open Web Text)

Max Activating Token Index: 76

Text #6

Max Range: 6.3790. Min Range: -6.3790

Max Act: 5.7002. Min Act: -0.1700

Data Index: 4245555 (Open Web Text)

Max Activating Token Index: 374

Text #7

Max Range: 6.3790. Min Range: -6.3790

Max Act: 5.6865. Min Act: -0.1700

Data Index: 6035752 (Open Web Text)

Max Activating Token Index: 155

Text #8

Max Range: 6.3790. Min Range: -6.3790

Max Act: 5.6645. Min Act: -0.1700

Data Index: 8634268 (Open Web Text)

Max Activating Token Index: 670

Text #9

Max Range: 6.3790. Min Range: -6.3790

Max Act: 5.5755. Min Act: -0.1700

Data Index: 7626213 (Open Web Text)

Max Activating Token Index: 24

Text #10

Max Range: 6.3790. Min Range: -6.3790

Max Act: 5.5793. Min Act: -0.1700

Data Index: 1813134 (Open Web Text)

Max Activating Token Index: 865

Text #11

Max Range: 6.3790. Min Range: -6.3790

Max Act: 5.5951. Min Act: -0.1700

Data Index: 1742398 (Open Web Text)

Max Activating Token Index: 171

Text #12

Max Range: 6.3790. Min Range: -6.3790

Max Act: 5.5885. Min Act: -0.1700

Data Index: 2985624 (Open Web Text)

Max Activating Token Index: 974

Text #13

Max Range: 6.3790. Min Range: -6.3790

Max Act: 5.5684. Min Act: -0.1700

Data Index: 2045137 (Open Web Text)

Max Activating Token Index: 810

Text #14

Max Range: 6.3790. Min Range: -6.3790

Max Act: 5.5713. Min Act: -0.1700

Data Index: 8290650 (Open Web Text)

Max Activating Token Index: 557

Text #15

Max Range: 6.3790. Min Range: -6.3790

Max Act: 5.6391. Min Act: -0.1700

Data Index: 3064505 (Open Web Text)

Max Activating Token Index: 990

Text #16

Max Range: 6.3790. Min Range: -6.3790

Max Act: 5.5669. Min Act: -0.1700

Data Index: 3198265 (Open Web Text)

Max Activating Token Index: 922

Text #17

Max Range: 6.3790. Min Range: -6.3790

Max Act: 5.5370. Min Act: -0.1700

Data Index: 1559519 (Open Web Text)

Max Activating Token Index: 923

Text #18

Max Range: 6.3790. Min Range: -6.3790

Max Act: 5.5533. Min Act: -0.1700

Data Index: 7994898 (Open Web Text)

Max Activating Token Index: 927

Text #19

Max Range: 6.3790. Min Range: -6.3790

Max Act: 5.5322. Min Act: -0.1700

Data Index: 1742821 (Open Web Text)

Max Activating Token Index: 758