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

Dataset: Open Web Text

Neuron 784 in Layer 5

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: 4.8379. Min Range: -4.8379

Max Act: 4.8379. Min Act: -0.1700

Data Index: 3695211 (Open Web Text)

Max Activating Token Index: 505

Text #1

Max Range: 4.8379. Min Range: -4.8379

Max Act: 4.8134. Min Act: -0.1700

Data Index: 173219 (Open Web Text)

Max Activating Token Index: 577

Text #2

Max Range: 4.8379. Min Range: -4.8379

Max Act: 4.4811. Min Act: -0.1700

Data Index: 3355824 (Open Web Text)

Max Activating Token Index: 679

Text #3

Max Range: 4.8379. Min Range: -4.8379

Max Act: 4.5115. Min Act: -0.1700

Data Index: 8443163 (Open Web Text)

Max Activating Token Index: 854

Text #4

Max Range: 4.8379. Min Range: -4.8379

Max Act: 4.4953. Min Act: -0.1700

Data Index: 6842087 (Open Web Text)

Max Activating Token Index: 948

Text #5

Max Range: 4.8379. Min Range: -4.8379

Max Act: 4.4752. Min Act: -0.1700

Data Index: 4314361 (Open Web Text)

Max Activating Token Index: 117

Text #6

Max Range: 4.8379. Min Range: -4.8379

Max Act: 4.4788. Min Act: -0.1700

Data Index: 7675399 (Open Web Text)

Max Activating Token Index: 234

Text #7

Max Range: 4.8379. Min Range: -4.8379

Max Act: 4.4342. Min Act: -0.1700

Data Index: 4257324 (Open Web Text)

Max Activating Token Index: 946

Text #8

Max Range: 4.8379. Min Range: -4.8379

Max Act: 4.4602. Min Act: -0.1700

Data Index: 3495403 (Open Web Text)

Max Activating Token Index: 555

Text #9

Max Range: 4.8379. Min Range: -4.8379

Max Act: 4.4327. Min Act: -0.1700

Data Index: 6253411 (Open Web Text)

Max Activating Token Index: 581

Text #10

Max Range: 4.8379. Min Range: -4.8379

Max Act: 4.4665. Min Act: -0.1700

Data Index: 7200918 (Open Web Text)

Max Activating Token Index: 558

Text #11

Max Range: 4.8379. Min Range: -4.8379

Max Act: 4.4255. Min Act: -0.1700

Data Index: 4975095 (Open Web Text)

Max Activating Token Index: 753

Text #12

Max Range: 4.8379. Min Range: -4.8379

Max Act: 4.4082. Min Act: -0.1700

Data Index: 3958669 (Open Web Text)

Max Activating Token Index: 983

Text #13

Max Range: 4.8379. Min Range: -4.8379

Max Act: 4.3894. Min Act: -0.1700

Data Index: 1629622 (Open Web Text)

Max Activating Token Index: 915

Text #14

Max Range: 4.8379. Min Range: -4.8379

Max Act: 4.3899. Min Act: -0.1700

Data Index: 4160592 (Open Web Text)

Max Activating Token Index: 996

Text #15

Max Range: 4.8379. Min Range: -4.8379

Max Act: 4.4078. Min Act: -0.1700

Data Index: 2411775 (Open Web Text)

Max Activating Token Index: 294

Text #16

Max Range: 4.8379. Min Range: -4.8379

Max Act: 4.4340. Min Act: -0.1700

Data Index: 5223361 (Open Web Text)

Max Activating Token Index: 638

Text #17

Max Range: 4.8379. Min Range: -4.8379

Max Act: 4.3905. Min Act: -0.1700

Data Index: 6860798 (Open Web Text)

Max Activating Token Index: 951

Text #18

Max Range: 4.8379. Min Range: -4.8379

Max Act: 4.4152. Min Act: -0.1700

Data Index: 5827534 (Open Web Text)

Max Activating Token Index: 688

Text #19

Max Range: 4.8379. Min Range: -4.8379

Max Act: 4.4073. Min Act: -0.1700

Data Index: 5619307 (Open Web Text)

Max Activating Token Index: 526