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

Dataset: Open Web Text

Neuron 370 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: 3.3762. Min Range: -3.3762

Max Act: 3.3762. Min Act: -0.1700

Data Index: 7292935 (Open Web Text)

Max Activating Token Index: 34

Text #1

Max Range: 3.3762. Min Range: -3.3762

Max Act: 3.3497. Min Act: -0.1700

Data Index: 4500331 (Open Web Text)

Max Activating Token Index: 710

Text #2

Max Range: 3.3762. Min Range: -3.3762

Max Act: 3.3036. Min Act: -0.1700

Data Index: 4403398 (Open Web Text)

Max Activating Token Index: 339

Text #3

Max Range: 3.3762. Min Range: -3.3762

Max Act: 3.3338. Min Act: -0.1700

Data Index: 5659728 (Open Web Text)

Max Activating Token Index: 785

Text #4

Max Range: 3.3762. Min Range: -3.3762

Max Act: 3.3154. Min Act: -0.1700

Data Index: 7904284 (Open Web Text)

Max Activating Token Index: 186

Text #5

Max Range: 3.3762. Min Range: -3.3762

Max Act: 3.2798. Min Act: -0.1700

Data Index: 6341028 (Open Web Text)

Max Activating Token Index: 708

Text #6

Max Range: 3.3762. Min Range: -3.3762

Max Act: 3.2906. Min Act: -0.1700

Data Index: 5028597 (Open Web Text)

Max Activating Token Index: 366

Text #7

Max Range: 3.3762. Min Range: -3.3762

Max Act: 3.2790. Min Act: -0.1700

Data Index: 304064 (Open Web Text)

Max Activating Token Index: 411

Text #8

Max Range: 3.3762. Min Range: -3.3762

Max Act: 3.2572. Min Act: -0.1700

Data Index: 792568 (Open Web Text)

Max Activating Token Index: 310

Text #9

Max Range: 3.3762. Min Range: -3.3762

Max Act: 3.2740. Min Act: -0.1700

Data Index: 4461655 (Open Web Text)

Max Activating Token Index: 656

Text #10

Max Range: 3.3762. Min Range: -3.3762

Max Act: 3.2413. Min Act: -0.1700

Data Index: 8026225 (Open Web Text)

Max Activating Token Index: 952

Text #11

Max Range: 3.3762. Min Range: -3.3762

Max Act: 3.2328. Min Act: -0.1700

Data Index: 4343173 (Open Web Text)

Max Activating Token Index: 710

Text #12

Max Range: 3.3762. Min Range: -3.3762

Max Act: 3.2125. Min Act: -0.1700

Data Index: 8651694 (Open Web Text)

Max Activating Token Index: 361

Text #13

Max Range: 3.3762. Min Range: -3.3762

Max Act: 3.2290. Min Act: -0.1700

Data Index: 8056971 (Open Web Text)

Max Activating Token Index: 541

Text #14

Max Range: 3.3762. Min Range: -3.3762

Max Act: 3.2162. Min Act: -0.1700

Data Index: 8058614 (Open Web Text)

Max Activating Token Index: 1006

Text #15

Max Range: 3.3762. Min Range: -3.3762

Max Act: 3.2076. Min Act: -0.1700

Data Index: 1772155 (Open Web Text)

Max Activating Token Index: 654

Text #16

Max Range: 3.3762. Min Range: -3.3762

Max Act: 3.1686. Min Act: -0.1700

Data Index: 4201713 (Open Web Text)

Max Activating Token Index: 376

Text #17

Max Range: 3.3762. Min Range: -3.3762

Max Act: 3.2062. Min Act: -0.1700

Data Index: 5665138 (Open Web Text)

Max Activating Token Index: 666

Text #18

Max Range: 3.3762. Min Range: -3.3762

Max Act: 3.2127. Min Act: -0.1700

Data Index: 4070897 (Open Web Text)

Max Activating Token Index: 851

Text #19

Max Range: 3.3762. Min Range: -3.3762

Max Act: 3.1865. Min Act: -0.1700

Data Index: 4748568 (Open Web Text)

Max Activating Token Index: 280