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

Dataset: Open Web Text

Neuron 2843 in Layer 3

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: 3.6115. Min Range: -3.6115

Max Act: 3.6115. Min Act: -0.1700

Data Index: 4060905 (Open Web Text)

Max Activating Token Index: 8

Text #1

Max Range: 3.6115. Min Range: -3.6115

Max Act: 3.4622. Min Act: -0.1700

Data Index: 8806853 (Open Web Text)

Max Activating Token Index: 597

Text #2

Max Range: 3.6115. Min Range: -3.6115

Max Act: 3.3853. Min Act: -0.1700

Data Index: 5088978 (Open Web Text)

Max Activating Token Index: 88

Text #3

Max Range: 3.6115. Min Range: -3.6115

Max Act: 3.3847. Min Act: -0.1700

Data Index: 5184793 (Open Web Text)

Max Activating Token Index: 14

Text #4

Max Range: 3.6115. Min Range: -3.6115

Max Act: 3.3421. Min Act: -0.1700

Data Index: 6272549 (Open Web Text)

Max Activating Token Index: 609

Text #5

Max Range: 3.6115. Min Range: -3.6115

Max Act: 3.3800. Min Act: -0.1700

Data Index: 3903866 (Open Web Text)

Max Activating Token Index: 24

Text #6

Max Range: 3.6115. Min Range: -3.6115

Max Act: 3.3136. Min Act: -0.1700

Data Index: 2206830 (Open Web Text)

Max Activating Token Index: 599

Text #7

Max Range: 3.6115. Min Range: -3.6115

Max Act: 3.3769. Min Act: -0.1700

Data Index: 3631478 (Open Web Text)

Max Activating Token Index: 198

Text #8

Max Range: 3.6115. Min Range: -3.6115

Max Act: 3.3654. Min Act: -0.1700

Data Index: 8314033 (Open Web Text)

Max Activating Token Index: 406

Text #9

Max Range: 3.6115. Min Range: -3.6115

Max Act: 3.3324. Min Act: -0.1700

Data Index: 4568371 (Open Web Text)

Max Activating Token Index: 894

Text #10

Max Range: 3.6115. Min Range: -3.6115

Max Act: 3.3117. Min Act: -0.1700

Data Index: 486987 (Open Web Text)

Max Activating Token Index: 633

Text #11

Max Range: 3.6115. Min Range: -3.6115

Max Act: 3.3765. Min Act: -0.1700

Data Index: 2235720 (Open Web Text)

Max Activating Token Index: 365

Text #12

Max Range: 3.6115. Min Range: -3.6115

Max Act: 3.3301. Min Act: -0.1700

Data Index: 1370744 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 3.6115. Min Range: -3.6115

Max Act: 3.3301. Min Act: -0.1700

Data Index: 3298960 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 3.6115. Min Range: -3.6115

Max Act: 3.3317. Min Act: -0.1700

Data Index: 67862 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 3.6115. Min Range: -3.6115

Max Act: 3.3301. Min Act: -0.1700

Data Index: 1118930 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 3.6115. Min Range: -3.6115

Max Act: 3.3301. Min Act: -0.1700

Data Index: 2277208 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 3.6115. Min Range: -3.6115

Max Act: 3.3301. Min Act: -0.1700

Data Index: 2978690 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 3.6115. Min Range: -3.6115

Max Act: 3.3206. Min Act: -0.1700

Data Index: 115588 (Open Web Text)

Max Activating Token Index: 799

Text #19

Max Range: 3.6115. Min Range: -3.6115

Max Act: 3.3301. Min Act: -0.1700

Data Index: 1741699 (Open Web Text)

Max Activating Token Index: 3