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

Dataset: Open Web Text

Neuron 2831 in Layer 3

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: 4.0900. Min Range: -4.0900

Max Act: 4.0900. Min Act: -0.1700

Data Index: 3465261 (Open Web Text)

Max Activating Token Index: 589

Text #1

Max Range: 4.0900. Min Range: -4.0900

Max Act: 4.0569. Min Act: -0.1700

Data Index: 6767578 (Open Web Text)

Max Activating Token Index: 121

Text #2

Max Range: 4.0900. Min Range: -4.0900

Max Act: 4.0617. Min Act: -0.1700

Data Index: 1199675 (Open Web Text)

Max Activating Token Index: 97

Text #3

Max Range: 4.0900. Min Range: -4.0900

Max Act: 4.0026. Min Act: -0.1700

Data Index: 4082969 (Open Web Text)

Max Activating Token Index: 44

Text #4

Max Range: 4.0900. Min Range: -4.0900

Max Act: 3.9469. Min Act: -0.1700

Data Index: 5082905 (Open Web Text)

Max Activating Token Index: 39

Text #5

Max Range: 4.0900. Min Range: -4.0900

Max Act: 3.9615. Min Act: -0.1700

Data Index: 6908409 (Open Web Text)

Max Activating Token Index: 609

Text #6

Max Range: 4.0900. Min Range: -4.0900

Max Act: 3.9544. Min Act: -0.1700

Data Index: 7549537 (Open Web Text)

Max Activating Token Index: 32

Text #7

Max Range: 4.0900. Min Range: -4.0900

Max Act: 3.9250. Min Act: -0.1700

Data Index: 6052495 (Open Web Text)

Max Activating Token Index: 63

Text #8

Max Range: 4.0900. Min Range: -4.0900

Max Act: 3.9366. Min Act: -0.1700

Data Index: 3324862 (Open Web Text)

Max Activating Token Index: 393

Text #9

Max Range: 4.0900. Min Range: -4.0900

Max Act: 3.9212. Min Act: -0.1700

Data Index: 168479 (Open Web Text)

Max Activating Token Index: 164

Text #10

Max Range: 4.0900. Min Range: -4.0900

Max Act: 3.8830. Min Act: -0.1700

Data Index: 3608961 (Open Web Text)

Max Activating Token Index: 710

Text #11

Max Range: 4.0900. Min Range: -4.0900

Max Act: 3.9047. Min Act: -0.1700

Data Index: 8780182 (Open Web Text)

Max Activating Token Index: 741

Text #12

Max Range: 4.0900. Min Range: -4.0900

Max Act: 3.8882. Min Act: -0.1700

Data Index: 5519178 (Open Web Text)

Max Activating Token Index: 769

Text #13

Max Range: 4.0900. Min Range: -4.0900

Max Act: 3.9359. Min Act: -0.1700

Data Index: 3912195 (Open Web Text)

Max Activating Token Index: 23

Text #14

Max Range: 4.0900. Min Range: -4.0900

Max Act: 3.8709. Min Act: -0.1700

Data Index: 5142020 (Open Web Text)

Max Activating Token Index: 30

Text #15

Max Range: 4.0900. Min Range: -4.0900

Max Act: 3.8750. Min Act: -0.1700

Data Index: 3831962 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 4.0900. Min Range: -4.0900

Max Act: 3.8731. Min Act: -0.1700

Data Index: 7634657 (Open Web Text)

Max Activating Token Index: 339

Text #17

Max Range: 4.0900. Min Range: -4.0900

Max Act: 3.8566. Min Act: -0.1700

Data Index: 3273997 (Open Web Text)

Max Activating Token Index: 649

Text #18

Max Range: 4.0900. Min Range: -4.0900

Max Act: 3.8667. Min Act: -0.1700

Data Index: 6249900 (Open Web Text)

Max Activating Token Index: 970

Text #19

Max Range: 4.0900. Min Range: -4.0900

Max Act: 3.8514. Min Act: -0.1700

Data Index: 47154 (Open Web Text)

Max Activating Token Index: 409