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

Dataset: Open Web Text

Neuron 2561 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: 3.6387. Min Range: -3.6387

Max Act: 3.6387. Min Act: -0.1700

Data Index: 6407492 (Open Web Text)

Max Activating Token Index: 936

Text #1

Max Range: 3.6387. Min Range: -3.6387

Max Act: 3.4471. Min Act: -0.1700

Data Index: 4147343 (Open Web Text)

Max Activating Token Index: 696

Text #2

Max Range: 3.6387. Min Range: -3.6387

Max Act: 3.4130. Min Act: -0.1700

Data Index: 4368332 (Open Web Text)

Max Activating Token Index: 864

Text #3

Max Range: 3.6387. Min Range: -3.6387

Max Act: 3.4229. Min Act: -0.1700

Data Index: 5044554 (Open Web Text)

Max Activating Token Index: 44

Text #4

Max Range: 3.6387. Min Range: -3.6387

Max Act: 3.4215. Min Act: -0.1700

Data Index: 6337871 (Open Web Text)

Max Activating Token Index: 386

Text #5

Max Range: 3.6387. Min Range: -3.6387

Max Act: 3.3984. Min Act: -0.1700

Data Index: 7353214 (Open Web Text)

Max Activating Token Index: 967

Text #6

Max Range: 3.6387. Min Range: -3.6387

Max Act: 3.3820. Min Act: -0.1700

Data Index: 6910478 (Open Web Text)

Max Activating Token Index: 920

Text #7

Max Range: 3.6387. Min Range: -3.6387

Max Act: 3.3787. Min Act: -0.1700

Data Index: 1593802 (Open Web Text)

Max Activating Token Index: 874

Text #8

Max Range: 3.6387. Min Range: -3.6387

Max Act: 3.3354. Min Act: -0.1700

Data Index: 2832215 (Open Web Text)

Max Activating Token Index: 279

Text #9

Max Range: 3.6387. Min Range: -3.6387

Max Act: 3.3626. Min Act: -0.1700

Data Index: 4549873 (Open Web Text)

Max Activating Token Index: 717

Text #10

Max Range: 3.6387. Min Range: -3.6387

Max Act: 3.3432. Min Act: -0.1700

Data Index: 8046191 (Open Web Text)

Max Activating Token Index: 485

Text #11

Max Range: 3.6387. Min Range: -3.6387

Max Act: 3.3291. Min Act: -0.1700

Data Index: 4068391 (Open Web Text)

Max Activating Token Index: 856

Text #12

Max Range: 3.6387. Min Range: -3.6387

Max Act: 3.3648. Min Act: -0.1700

Data Index: 8324527 (Open Web Text)

Max Activating Token Index: 920

Text #13

Max Range: 3.6387. Min Range: -3.6387

Max Act: 3.3418. Min Act: -0.1700

Data Index: 1491539 (Open Web Text)

Max Activating Token Index: 786

Text #14

Max Range: 3.6387. Min Range: -3.6387

Max Act: 3.3257. Min Act: -0.1700

Data Index: 6061937 (Open Web Text)

Max Activating Token Index: 926

Text #15

Max Range: 3.6387. Min Range: -3.6387

Max Act: 3.2875. Min Act: -0.1700

Data Index: 4024718 (Open Web Text)

Max Activating Token Index: 580

Text #16

Max Range: 3.6387. Min Range: -3.6387

Max Act: 3.3338. Min Act: -0.1700

Data Index: 8534937 (Open Web Text)

Max Activating Token Index: 832

Text #17

Max Range: 3.6387. Min Range: -3.6387

Max Act: 3.3376. Min Act: -0.1700

Data Index: 3360804 (Open Web Text)

Max Activating Token Index: 730

Text #18

Max Range: 3.6387. Min Range: -3.6387

Max Act: 3.3484. Min Act: -0.1700

Data Index: 1367468 (Open Web Text)

Max Activating Token Index: 725

Text #19

Max Range: 3.6387. Min Range: -3.6387

Max Act: 3.3238. Min Act: -0.1700

Data Index: 6132022 (Open Web Text)

Max Activating Token Index: 841