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

Dataset: Open Web Text

Neuron 2310 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: 3.7387. Min Range: -3.7387

Max Act: 3.7387. Min Act: -0.1700

Data Index: 1124878 (Open Web Text)

Max Activating Token Index: 883

Text #1

Max Range: 3.7387. Min Range: -3.7387

Max Act: 3.7027. Min Act: -0.1700

Data Index: 8763322 (Open Web Text)

Max Activating Token Index: 732

Text #2

Max Range: 3.7387. Min Range: -3.7387

Max Act: 3.5955. Min Act: -0.1700

Data Index: 3148585 (Open Web Text)

Max Activating Token Index: 349

Text #3

Max Range: 3.7387. Min Range: -3.7387

Max Act: 3.5813. Min Act: -0.1700

Data Index: 222560 (Open Web Text)

Max Activating Token Index: 437

Text #4

Max Range: 3.7387. Min Range: -3.7387

Max Act: 3.5862. Min Act: -0.1700

Data Index: 6034729 (Open Web Text)

Max Activating Token Index: 820

Text #5

Max Range: 3.7387. Min Range: -3.7387

Max Act: 3.5468. Min Act: -0.1700

Data Index: 6576915 (Open Web Text)

Max Activating Token Index: 280

Text #6

Max Range: 3.7387. Min Range: -3.7387

Max Act: 3.5389. Min Act: -0.1700

Data Index: 7615323 (Open Web Text)

Max Activating Token Index: 1022

Text #7

Max Range: 3.7387. Min Range: -3.7387

Max Act: 3.5349. Min Act: -0.1700

Data Index: 2823222 (Open Web Text)

Max Activating Token Index: 537

Text #8

Max Range: 3.7387. Min Range: -3.7387

Max Act: 3.5091. Min Act: -0.1700

Data Index: 7737957 (Open Web Text)

Max Activating Token Index: 774

Text #9

Max Range: 3.7387. Min Range: -3.7387

Max Act: 3.5058. Min Act: -0.1700

Data Index: 6141031 (Open Web Text)

Max Activating Token Index: 228

Text #10

Max Range: 3.7387. Min Range: -3.7387

Max Act: 3.4926. Min Act: -0.1700

Data Index: 5977920 (Open Web Text)

Max Activating Token Index: 630

Text #11

Max Range: 3.7387. Min Range: -3.7387

Max Act: 3.4916. Min Act: -0.1700

Data Index: 2038042 (Open Web Text)

Max Activating Token Index: 640

Text #12

Max Range: 3.7387. Min Range: -3.7387

Max Act: 3.4985. Min Act: -0.1700

Data Index: 2988732 (Open Web Text)

Max Activating Token Index: 480

Text #13

Max Range: 3.7387. Min Range: -3.7387

Max Act: 3.4692. Min Act: -0.1700

Data Index: 4626408 (Open Web Text)

Max Activating Token Index: 248

Text #14

Max Range: 3.7387. Min Range: -3.7387

Max Act: 3.4871. Min Act: -0.1700

Data Index: 4073641 (Open Web Text)

Max Activating Token Index: 913

Text #15

Max Range: 3.7387. Min Range: -3.7387

Max Act: 3.4582. Min Act: -0.1700

Data Index: 5543725 (Open Web Text)

Max Activating Token Index: 645

Text #16

Max Range: 3.7387. Min Range: -3.7387

Max Act: 3.4408. Min Act: -0.1700

Data Index: 2969309 (Open Web Text)

Max Activating Token Index: 461

Text #17

Max Range: 3.7387. Min Range: -3.7387

Max Act: 3.4416. Min Act: -0.1700

Data Index: 5512272 (Open Web Text)

Max Activating Token Index: 195

Text #18

Max Range: 3.7387. Min Range: -3.7387

Max Act: 3.4577. Min Act: -0.1700

Data Index: 7711183 (Open Web Text)

Max Activating Token Index: 852

Text #19

Max Range: 3.7387. Min Range: -3.7387

Max Act: 3.4554. Min Act: -0.1700

Data Index: 4195172 (Open Web Text)

Max Activating Token Index: 396