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

Dataset: Open Web Text

Neuron 561 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: 4.4998. Min Range: -4.4998

Max Act: 4.4998. Min Act: -0.1700

Data Index: 2714570 (Open Web Text)

Max Activating Token Index: 97

Text #1

Max Range: 4.4998. Min Range: -4.4998

Max Act: 4.4598. Min Act: -0.1700

Data Index: 3941819 (Open Web Text)

Max Activating Token Index: 58

Text #2

Max Range: 4.4998. Min Range: -4.4998

Max Act: 4.3741. Min Act: -0.1700

Data Index: 7260374 (Open Web Text)

Max Activating Token Index: 214

Text #3

Max Range: 4.4998. Min Range: -4.4998

Max Act: 4.3725. Min Act: -0.1700

Data Index: 4162931 (Open Web Text)

Max Activating Token Index: 340

Text #4

Max Range: 4.4998. Min Range: -4.4998

Max Act: 4.3679. Min Act: -0.1700

Data Index: 2945577 (Open Web Text)

Max Activating Token Index: 381

Text #5

Max Range: 4.4998. Min Range: -4.4998

Max Act: 4.3881. Min Act: -0.1700

Data Index: 2440808 (Open Web Text)

Max Activating Token Index: 524

Text #6

Max Range: 4.4998. Min Range: -4.4998

Max Act: 4.3874. Min Act: -0.1700

Data Index: 972873 (Open Web Text)

Max Activating Token Index: 939

Text #7

Max Range: 4.4998. Min Range: -4.4998

Max Act: 4.3597. Min Act: -0.1700

Data Index: 2363446 (Open Web Text)

Max Activating Token Index: 414

Text #8

Max Range: 4.4998. Min Range: -4.4998

Max Act: 4.3747. Min Act: -0.1700

Data Index: 8063895 (Open Web Text)

Max Activating Token Index: 550

Text #9

Max Range: 4.4998. Min Range: -4.4998

Max Act: 4.3212. Min Act: -0.1700

Data Index: 4012113 (Open Web Text)

Max Activating Token Index: 160

Text #10

Max Range: 4.4998. Min Range: -4.4998

Max Act: 4.3314. Min Act: -0.1700

Data Index: 2878124 (Open Web Text)

Max Activating Token Index: 105

Text #11

Max Range: 4.4998. Min Range: -4.4998

Max Act: 4.3235. Min Act: -0.1700

Data Index: 6506026 (Open Web Text)

Max Activating Token Index: 112

Text #12

Max Range: 4.4998. Min Range: -4.4998

Max Act: 4.3265. Min Act: -0.1700

Data Index: 3896204 (Open Web Text)

Max Activating Token Index: 754

Text #13

Max Range: 4.4998. Min Range: -4.4998

Max Act: 4.2813. Min Act: -0.1700

Data Index: 2734554 (Open Web Text)

Max Activating Token Index: 636

Text #14

Max Range: 4.4998. Min Range: -4.4998

Max Act: 4.3405. Min Act: -0.1700

Data Index: 4810910 (Open Web Text)

Max Activating Token Index: 698

Text #15

Max Range: 4.4998. Min Range: -4.4998

Max Act: 4.2274. Min Act: -0.1700

Data Index: 6884429 (Open Web Text)

Max Activating Token Index: 966

Text #16

Max Range: 4.4998. Min Range: -4.4998

Max Act: 4.2737. Min Act: -0.1700

Data Index: 3406930 (Open Web Text)

Max Activating Token Index: 781

Text #17

Max Range: 4.4998. Min Range: -4.4998

Max Act: 4.1971. Min Act: -0.1700

Data Index: 6909419 (Open Web Text)

Max Activating Token Index: 512

Text #18

Max Range: 4.4998. Min Range: -4.4998

Max Act: 4.2373. Min Act: -0.1700

Data Index: 3668935 (Open Web Text)

Max Activating Token Index: 853

Text #19

Max Range: 4.4998. Min Range: -4.4998

Max Act: 4.2056. Min Act: -0.1700

Data Index: 4694395 (Open Web Text)

Max Activating Token Index: 605