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

Dataset: Open Web Text

Neuron 1733 in Layer 4

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: 3.0944. Min Range: -3.0944

Max Act: 3.0944. Min Act: -0.1700

Data Index: 2286024 (Open Web Text)

Max Activating Token Index: 199

Text #1

Max Range: 3.0944. Min Range: -3.0944

Max Act: 3.0678. Min Act: -0.1700

Data Index: 7034036 (Open Web Text)

Max Activating Token Index: 344

Text #2

Max Range: 3.0944. Min Range: -3.0944

Max Act: 3.0497. Min Act: -0.1700

Data Index: 4552650 (Open Web Text)

Max Activating Token Index: 515

Text #3

Max Range: 3.0944. Min Range: -3.0944

Max Act: 3.0029. Min Act: -0.1700

Data Index: 1715157 (Open Web Text)

Max Activating Token Index: 354

Text #4

Max Range: 3.0944. Min Range: -3.0944

Max Act: 3.0037. Min Act: -0.1700

Data Index: 6909618 (Open Web Text)

Max Activating Token Index: 629

Text #5

Max Range: 3.0944. Min Range: -3.0944

Max Act: 3.0073. Min Act: -0.1700

Data Index: 2024265 (Open Web Text)

Max Activating Token Index: 642

Text #6

Max Range: 3.0944. Min Range: -3.0944

Max Act: 2.9713. Min Act: -0.1700

Data Index: 4719406 (Open Web Text)

Max Activating Token Index: 62

Text #7

Max Range: 3.0944. Min Range: -3.0944

Max Act: 2.9923. Min Act: -0.1700

Data Index: 7174883 (Open Web Text)

Max Activating Token Index: 321

Text #8

Max Range: 3.0944. Min Range: -3.0944

Max Act: 2.9453. Min Act: -0.1700

Data Index: 4321936 (Open Web Text)

Max Activating Token Index: 42

Text #9

Max Range: 3.0944. Min Range: -3.0944

Max Act: 2.9254. Min Act: -0.1700

Data Index: 8125899 (Open Web Text)

Max Activating Token Index: 643

Text #10

Max Range: 3.0944. Min Range: -3.0944

Max Act: 2.9158. Min Act: -0.1700

Data Index: 5579329 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 3.0944. Min Range: -3.0944

Max Act: 2.9158. Min Act: -0.1700

Data Index: 3651032 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 3.0944. Min Range: -3.0944

Max Act: 2.8983. Min Act: -0.1700

Data Index: 8645591 (Open Web Text)

Max Activating Token Index: 577

Text #13

Max Range: 3.0944. Min Range: -3.0944

Max Act: 2.9020. Min Act: -0.1700

Data Index: 2782654 (Open Web Text)

Max Activating Token Index: 974

Text #14

Max Range: 3.0944. Min Range: -3.0944

Max Act: 2.9276. Min Act: -0.1700

Data Index: 2570878 (Open Web Text)

Max Activating Token Index: 466

Text #15

Max Range: 3.0944. Min Range: -3.0944

Max Act: 2.9004. Min Act: -0.1700

Data Index: 2249704 (Open Web Text)

Max Activating Token Index: 930

Text #16

Max Range: 3.0944. Min Range: -3.0944

Max Act: 2.9083. Min Act: -0.1700

Data Index: 4145889 (Open Web Text)

Max Activating Token Index: 480

Text #17

Max Range: 3.0944. Min Range: -3.0944

Max Act: 2.8883. Min Act: -0.1700

Data Index: 2296870 (Open Web Text)

Max Activating Token Index: 120

Text #18

Max Range: 3.0944. Min Range: -3.0944

Max Act: 2.9210. Min Act: -0.1700

Data Index: 6299915 (Open Web Text)

Max Activating Token Index: 825

Text #19

Max Range: 3.0944. Min Range: -3.0944

Max Act: 2.9008. Min Act: -0.1700

Data Index: 7539700 (Open Web Text)

Max Activating Token Index: 775