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

Dataset: Open Web Text

Neuron 559 in Layer 1

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: 3.5405. Min Range: -3.5405

Max Act: 3.5405. Min Act: -0.1700

Data Index: 3801857 (Open Web Text)

Max Activating Token Index: 235

Text #1

Max Range: 3.5405. Min Range: -3.5405

Max Act: 3.4903. Min Act: -0.1700

Data Index: 2233404 (Open Web Text)

Max Activating Token Index: 744

Text #2

Max Range: 3.5405. Min Range: -3.5405

Max Act: 3.4653. Min Act: -0.1593

Data Index: 2233452 (Open Web Text)

Max Activating Token Index: 945

Text #3

Max Range: 3.5405. Min Range: -3.5405

Max Act: 3.4475. Min Act: -0.1593

Data Index: 2233454 (Open Web Text)

Max Activating Token Index: 975

Text #4

Max Range: 3.5405. Min Range: -3.5405

Max Act: 3.4494. Min Act: -0.1700

Data Index: 2233453 (Open Web Text)

Max Activating Token Index: 960

Text #5

Max Range: 3.5405. Min Range: -3.5405

Max Act: 3.4490. Min Act: -0.1700

Data Index: 7008806 (Open Web Text)

Max Activating Token Index: 807

Text #6

Max Range: 3.5405. Min Range: -3.5405

Max Act: 3.4479. Min Act: -0.1700

Data Index: 1807416 (Open Web Text)

Max Activating Token Index: 607

Text #7

Max Range: 3.5405. Min Range: -3.5405

Max Act: 3.4432. Min Act: -0.1700

Data Index: 2233455 (Open Web Text)

Max Activating Token Index: 990

Text #8

Max Range: 3.5405. Min Range: -3.5405

Max Act: 3.4252. Min Act: -0.1700

Data Index: 2233457 (Open Web Text)

Max Activating Token Index: 501

Text #9

Max Range: 3.5405. Min Range: -3.5405

Max Act: 3.4280. Min Act: -0.1593

Data Index: 2233456 (Open Web Text)

Max Activating Token Index: 1005

Text #10

Max Range: 3.5405. Min Range: -3.5405

Max Act: 3.4093. Min Act: -0.1593

Data Index: 2233405 (Open Web Text)

Max Activating Token Index: 240

Text #11

Max Range: 3.5405. Min Range: -3.5405

Max Act: 3.4093. Min Act: -0.1593

Data Index: 2233450 (Open Web Text)

Max Activating Token Index: 396

Text #12

Max Range: 3.5405. Min Range: -3.5405

Max Act: 3.4187. Min Act: -0.1700

Data Index: 2233451 (Open Web Text)

Max Activating Token Index: 930

Text #13

Max Range: 3.5405. Min Range: -3.5405

Max Act: 3.4026. Min Act: -0.1593

Data Index: 2233458 (Open Web Text)

Max Activating Token Index: 516

Text #14

Max Range: 3.5405. Min Range: -3.5405

Max Act: 3.4027. Min Act: -0.1700

Data Index: 3801858 (Open Web Text)

Max Activating Token Index: 397

Text #15

Max Range: 3.5405. Min Range: -3.5405

Max Act: 3.4050. Min Act: -0.1700

Data Index: 3087929 (Open Web Text)

Max Activating Token Index: 322

Text #16

Max Range: 3.5405. Min Range: -3.5405

Max Act: 3.3738. Min Act: -0.1699

Data Index: 2233448 (Open Web Text)

Max Activating Token Index: 366

Text #17

Max Range: 3.5405. Min Range: -3.5405

Max Act: 3.3922. Min Act: -0.1700

Data Index: 2233429 (Open Web Text)

Max Activating Token Index: 600

Text #18

Max Range: 3.5405. Min Range: -3.5405

Max Act: 3.3878. Min Act: -0.1698

Data Index: 1966356 (Open Web Text)

Max Activating Token Index: 632

Text #19

Max Range: 3.5405. Min Range: -3.5405

Max Act: 3.3973. Min Act: -0.1700

Data Index: 1807414 (Open Web Text)

Max Activating Token Index: 301