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

Dataset: Open Web Text

Neuron 1617 in Layer 0

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: 2.9304. Min Range: -2.9304

Max Act: 2.9304. Min Act: -0.1700

Data Index: 7273094 (Open Web Text)

Max Activating Token Index: 519

Text #1

Max Range: 2.9304. Min Range: -2.9304

Max Act: 2.8969. Min Act: -0.1700

Data Index: 6516000 (Open Web Text)

Max Activating Token Index: 528

Text #2

Max Range: 2.9304. Min Range: -2.9304

Max Act: 2.8578. Min Act: -0.1700

Data Index: 1790141 (Open Web Text)

Max Activating Token Index: 794

Text #3

Max Range: 2.9304. Min Range: -2.9304

Max Act: 2.8204. Min Act: -0.1700

Data Index: 8389510 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 2.9304. Min Range: -2.9304

Max Act: 2.8037. Min Act: -0.1700

Data Index: 3964700 (Open Web Text)

Max Activating Token Index: 721

Text #5

Max Range: 2.9304. Min Range: -2.9304

Max Act: 2.8040. Min Act: -0.1700

Data Index: 6414332 (Open Web Text)

Max Activating Token Index: 778

Text #6

Max Range: 2.9304. Min Range: -2.9304

Max Act: 2.7794. Min Act: -0.1700

Data Index: 1069545 (Open Web Text)

Max Activating Token Index: 711

Text #7

Max Range: 2.9304. Min Range: -2.9304

Max Act: 2.7962. Min Act: -0.1700

Data Index: 3964701 (Open Web Text)

Max Activating Token Index: 226

Text #8

Max Range: 2.9304. Min Range: -2.9304

Max Act: 2.7511. Min Act: -0.1700

Data Index: 5014913 (Open Web Text)

Max Activating Token Index: 616

Text #9

Max Range: 2.9304. Min Range: -2.9304

Max Act: 2.7572. Min Act: -0.1700

Data Index: 2517653 (Open Web Text)

Max Activating Token Index: 595

Text #10

Max Range: 2.9304. Min Range: -2.9304

Max Act: 2.7710. Min Act: -0.1700

Data Index: 6654839 (Open Web Text)

Max Activating Token Index: 677

Text #11

Max Range: 2.9304. Min Range: -2.9304

Max Act: 2.7741. Min Act: -0.1700

Data Index: 4099543 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 2.9304. Min Range: -2.9304

Max Act: 2.7605. Min Act: -0.1700

Data Index: 6903222 (Open Web Text)

Max Activating Token Index: 551

Text #13

Max Range: 2.9304. Min Range: -2.9304

Max Act: 2.7569. Min Act: -0.1700

Data Index: 3964702 (Open Web Text)

Max Activating Token Index: 18

Text #14

Max Range: 2.9304. Min Range: -2.9304

Max Act: 2.7535. Min Act: -0.1700

Data Index: 5100288 (Open Web Text)

Max Activating Token Index: 243

Text #15

Max Range: 2.9304. Min Range: -2.9304

Max Act: 2.7342. Min Act: -0.1700

Data Index: 3752511 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 2.9304. Min Range: -2.9304

Max Act: 2.7215. Min Act: -0.1700

Data Index: 4790818 (Open Web Text)

Max Activating Token Index: 669

Text #17

Max Range: 2.9304. Min Range: -2.9304

Max Act: 2.7232. Min Act: -0.1700

Data Index: 2929098 (Open Web Text)

Max Activating Token Index: 258

Text #18

Max Range: 2.9304. Min Range: -2.9304

Max Act: 2.7297. Min Act: -0.1700

Data Index: 917961 (Open Web Text)

Max Activating Token Index: 74

Text #19

Max Range: 2.9304. Min Range: -2.9304

Max Act: 2.7304. Min Act: -0.1700

Data Index: 1029403 (Open Web Text)

Max Activating Token Index: 41