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

Dataset: Open Web Text

Neuron 1700 in Layer 6

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: 4.7617. Min Range: -4.7617

Max Act: 4.7617. Min Act: -0.1700

Data Index: 2084170 (Open Web Text)

Max Activating Token Index: 1009

Text #1

Max Range: 4.7617. Min Range: -4.7617

Max Act: 4.6200. Min Act: -0.1700

Data Index: 6124870 (Open Web Text)

Max Activating Token Index: 454

Text #2

Max Range: 4.7617. Min Range: -4.7617

Max Act: 4.6032. Min Act: -0.1700

Data Index: 1824078 (Open Web Text)

Max Activating Token Index: 466

Text #3

Max Range: 4.7617. Min Range: -4.7617

Max Act: 4.5833. Min Act: -0.1700

Data Index: 7560709 (Open Web Text)

Max Activating Token Index: 689

Text #4

Max Range: 4.7617. Min Range: -4.7617

Max Act: 4.5908. Min Act: -0.1700

Data Index: 7879445 (Open Web Text)

Max Activating Token Index: 182

Text #5

Max Range: 4.7617. Min Range: -4.7617

Max Act: 4.5617. Min Act: -0.1700

Data Index: 5103040 (Open Web Text)

Max Activating Token Index: 863

Text #6

Max Range: 4.7617. Min Range: -4.7617

Max Act: 4.5784. Min Act: -0.1700

Data Index: 7140435 (Open Web Text)

Max Activating Token Index: 456

Text #7

Max Range: 4.7617. Min Range: -4.7617

Max Act: 4.5841. Min Act: -0.1700

Data Index: 7508492 (Open Web Text)

Max Activating Token Index: 335

Text #8

Max Range: 4.7617. Min Range: -4.7617

Max Act: 4.5305. Min Act: -0.1700

Data Index: 5877979 (Open Web Text)

Max Activating Token Index: 490

Text #9

Max Range: 4.7617. Min Range: -4.7617

Max Act: 4.5243. Min Act: -0.1700

Data Index: 5726919 (Open Web Text)

Max Activating Token Index: 631

Text #10

Max Range: 4.7617. Min Range: -4.7617

Max Act: 4.5392. Min Act: -0.1700

Data Index: 2516938 (Open Web Text)

Max Activating Token Index: 500

Text #11

Max Range: 4.7617. Min Range: -4.7617

Max Act: 4.5368. Min Act: -0.1700

Data Index: 7835094 (Open Web Text)

Max Activating Token Index: 712

Text #12

Max Range: 4.7617. Min Range: -4.7617

Max Act: 4.5140. Min Act: -0.1700

Data Index: 492464 (Open Web Text)

Max Activating Token Index: 734

Text #13

Max Range: 4.7617. Min Range: -4.7617

Max Act: 4.4950. Min Act: -0.1700

Data Index: 507270 (Open Web Text)

Max Activating Token Index: 130

Text #14

Max Range: 4.7617. Min Range: -4.7617

Max Act: 4.5287. Min Act: -0.1700

Data Index: 8419090 (Open Web Text)

Max Activating Token Index: 608

Text #15

Max Range: 4.7617. Min Range: -4.7617

Max Act: 4.4963. Min Act: -0.1700

Data Index: 7306723 (Open Web Text)

Max Activating Token Index: 407

Text #16

Max Range: 4.7617. Min Range: -4.7617

Max Act: 4.4968. Min Act: -0.1700

Data Index: 4505916 (Open Web Text)

Max Activating Token Index: 381

Text #17

Max Range: 4.7617. Min Range: -4.7617

Max Act: 4.4611. Min Act: -0.1700

Data Index: 7034715 (Open Web Text)

Max Activating Token Index: 636

Text #18

Max Range: 4.7617. Min Range: -4.7617

Max Act: 4.4740. Min Act: -0.1700

Data Index: 944234 (Open Web Text)

Max Activating Token Index: 831

Text #19

Max Range: 4.7617. Min Range: -4.7617

Max Act: 4.4812. Min Act: -0.1700

Data Index: 7358978 (Open Web Text)

Max Activating Token Index: 263