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

Dataset: Open Web Text

Neuron 3025 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: 4.4896. Min Range: -4.4896

Max Act: 4.4896. Min Act: -0.1700

Data Index: 1454390 (Open Web Text)

Max Activating Token Index: 637

Text #1

Max Range: 4.4896. Min Range: -4.4896

Max Act: 4.4392. Min Act: -0.1700

Data Index: 5597668 (Open Web Text)

Max Activating Token Index: 309

Text #2

Max Range: 4.4896. Min Range: -4.4896

Max Act: 4.4430. Min Act: -0.1700

Data Index: 1297004 (Open Web Text)

Max Activating Token Index: 426

Text #3

Max Range: 4.4896. Min Range: -4.4896

Max Act: 4.3989. Min Act: -0.1700

Data Index: 2265727 (Open Web Text)

Max Activating Token Index: 954

Text #4

Max Range: 4.4896. Min Range: -4.4896

Max Act: 4.3760. Min Act: -0.1700

Data Index: 1720275 (Open Web Text)

Max Activating Token Index: 127

Text #5

Max Range: 4.4896. Min Range: -4.4896

Max Act: 4.3595. Min Act: -0.1700

Data Index: 479423 (Open Web Text)

Max Activating Token Index: 538

Text #6

Max Range: 4.4896. Min Range: -4.4896

Max Act: 4.3445. Min Act: -0.1700

Data Index: 8621598 (Open Web Text)

Max Activating Token Index: 746

Text #7

Max Range: 4.4896. Min Range: -4.4896

Max Act: 4.3340. Min Act: -0.1700

Data Index: 4257575 (Open Web Text)

Max Activating Token Index: 294

Text #8

Max Range: 4.4896. Min Range: -4.4896

Max Act: 4.2682. Min Act: -0.1700

Data Index: 3596857 (Open Web Text)

Max Activating Token Index: 207

Text #9

Max Range: 4.4896. Min Range: -4.4896

Max Act: 4.2588. Min Act: -0.1700

Data Index: 562356 (Open Web Text)

Max Activating Token Index: 805

Text #10

Max Range: 4.4896. Min Range: -4.4896

Max Act: 4.2880. Min Act: -0.1700

Data Index: 7381640 (Open Web Text)

Max Activating Token Index: 92

Text #11

Max Range: 4.4896. Min Range: -4.4896

Max Act: 4.2586. Min Act: -0.1700

Data Index: 8105408 (Open Web Text)

Max Activating Token Index: 608

Text #12

Max Range: 4.4896. Min Range: -4.4896

Max Act: 4.2182. Min Act: -0.1700

Data Index: 2380877 (Open Web Text)

Max Activating Token Index: 923

Text #13

Max Range: 4.4896. Min Range: -4.4896

Max Act: 4.2319. Min Act: -0.1700

Data Index: 390869 (Open Web Text)

Max Activating Token Index: 1023

Text #14

Max Range: 4.4896. Min Range: -4.4896

Max Act: 4.1632. Min Act: -0.1700

Data Index: 4876007 (Open Web Text)

Max Activating Token Index: 371

Text #15

Max Range: 4.4896. Min Range: -4.4896

Max Act: 4.1596. Min Act: -0.1700

Data Index: 2652367 (Open Web Text)

Max Activating Token Index: 961

Text #16

Max Range: 4.4896. Min Range: -4.4896

Max Act: 4.1773. Min Act: -0.1700

Data Index: 5613585 (Open Web Text)

Max Activating Token Index: 244

Text #17

Max Range: 4.4896. Min Range: -4.4896

Max Act: 4.1689. Min Act: -0.1700

Data Index: 2348295 (Open Web Text)

Max Activating Token Index: 138

Text #18

Max Range: 4.4896. Min Range: -4.4896

Max Act: 4.1798. Min Act: -0.1700

Data Index: 4144850 (Open Web Text)

Max Activating Token Index: 817

Text #19

Max Range: 4.4896. Min Range: -4.4896

Max Act: 4.1080. Min Act: -0.1700

Data Index: 3565426 (Open Web Text)

Max Activating Token Index: 264