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

Dataset: Open Web Text

Neuron 513 in Layer 1

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: 1.5658. Min Range: -1.5658

Max Act: 1.5658. Min Act: -0.1700

Data Index: 7363450 (Open Web Text)

Max Activating Token Index: 750

Text #1

Max Range: 1.5658. Min Range: -1.5658

Max Act: 1.5347. Min Act: -0.1700

Data Index: 1382669 (Open Web Text)

Max Activating Token Index: 365

Text #2

Max Range: 1.5658. Min Range: -1.5658

Max Act: 1.5127. Min Act: -0.1700

Data Index: 6486119 (Open Web Text)

Max Activating Token Index: 260

Text #3

Max Range: 1.5658. Min Range: -1.5658

Max Act: 1.5212. Min Act: -0.1700

Data Index: 7759418 (Open Web Text)

Max Activating Token Index: 1015

Text #4

Max Range: 1.5658. Min Range: -1.5658

Max Act: 1.5116. Min Act: -0.1700

Data Index: 7341935 (Open Web Text)

Max Activating Token Index: 968

Text #5

Max Range: 1.5658. Min Range: -1.5658

Max Act: 1.5181. Min Act: -0.1700

Data Index: 2562554 (Open Web Text)

Max Activating Token Index: 1006

Text #6

Max Range: 1.5658. Min Range: -1.5658

Max Act: 1.5143. Min Act: -0.1700

Data Index: 4841405 (Open Web Text)

Max Activating Token Index: 547

Text #7

Max Range: 1.5658. Min Range: -1.5658

Max Act: 1.4942. Min Act: -0.1700

Data Index: 7306811 (Open Web Text)

Max Activating Token Index: 182

Text #8

Max Range: 1.5658. Min Range: -1.5658

Max Act: 1.4774. Min Act: -0.1700

Data Index: 1702425 (Open Web Text)

Max Activating Token Index: 1020

Text #9

Max Range: 1.5658. Min Range: -1.5658

Max Act: 1.4882. Min Act: -0.1700

Data Index: 6253574 (Open Web Text)

Max Activating Token Index: 554

Text #10

Max Range: 1.5658. Min Range: -1.5658

Max Act: 1.4703. Min Act: -0.1699

Data Index: 5457375 (Open Web Text)

Max Activating Token Index: 913

Text #11

Max Range: 1.5658. Min Range: -1.5658

Max Act: 1.4797. Min Act: -0.1700

Data Index: 490729 (Open Web Text)

Max Activating Token Index: 1020

Text #12

Max Range: 1.5658. Min Range: -1.5658

Max Act: 1.4693. Min Act: -0.1700

Data Index: 3995205 (Open Web Text)

Max Activating Token Index: 402

Text #13

Max Range: 1.5658. Min Range: -1.5658

Max Act: 1.4839. Min Act: -0.1700

Data Index: 2354892 (Open Web Text)

Max Activating Token Index: 1015

Text #14

Max Range: 1.5658. Min Range: -1.5658

Max Act: 1.4809. Min Act: -0.1700

Data Index: 6498865 (Open Web Text)

Max Activating Token Index: 479

Text #15

Max Range: 1.5658. Min Range: -1.5658

Max Act: 1.4810. Min Act: -0.1700

Data Index: 5706673 (Open Web Text)

Max Activating Token Index: 1002

Text #16

Max Range: 1.5658. Min Range: -1.5658

Max Act: 1.4736. Min Act: -0.1700

Data Index: 812662 (Open Web Text)

Max Activating Token Index: 487

Text #17

Max Range: 1.5658. Min Range: -1.5658

Max Act: 1.4666. Min Act: -0.1700

Data Index: 3563858 (Open Web Text)

Max Activating Token Index: 1014

Text #18

Max Range: 1.5658. Min Range: -1.5658

Max Act: 1.4649. Min Act: -0.1700

Data Index: 5565744 (Open Web Text)

Max Activating Token Index: 32

Text #19

Max Range: 1.5658. Min Range: -1.5658

Max Act: 1.4683. Min Act: -0.1700

Data Index: 4513950 (Open Web Text)

Max Activating Token Index: 467