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

Dataset: Open Web Text

Neuron 2022 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: 1.6490. Min Range: -1.6490

Max Act: 1.6490. Min Act: -0.1700

Data Index: 7101429 (Open Web Text)

Max Activating Token Index: 197

Text #1

Max Range: 1.6490. Min Range: -1.6490

Max Act: 1.4971. Min Act: -0.1700

Data Index: 1995006 (Open Web Text)

Max Activating Token Index: 62

Text #2

Max Range: 1.6490. Min Range: -1.6490

Max Act: 1.4899. Min Act: -0.1700

Data Index: 4860025 (Open Web Text)

Max Activating Token Index: 706

Text #3

Max Range: 1.6490. Min Range: -1.6490

Max Act: 1.4940. Min Act: -0.1700

Data Index: 2173387 (Open Web Text)

Max Activating Token Index: 100

Text #4

Max Range: 1.6490. Min Range: -1.6490

Max Act: 1.4839. Min Act: -0.1700

Data Index: 866204 (Open Web Text)

Max Activating Token Index: 1020

Text #5

Max Range: 1.6490. Min Range: -1.6490

Max Act: 1.4901. Min Act: -0.1699

Data Index: 2565978 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 1.6490. Min Range: -1.6490

Max Act: 1.4724. Min Act: -0.1700

Data Index: 3307018 (Open Web Text)

Max Activating Token Index: 54

Text #7

Max Range: 1.6490. Min Range: -1.6490

Max Act: 1.4759. Min Act: -0.1700

Data Index: 5019398 (Open Web Text)

Max Activating Token Index: 961

Text #8

Max Range: 1.6490. Min Range: -1.6490

Max Act: 1.4770. Min Act: -0.1700

Data Index: 2797301 (Open Web Text)

Max Activating Token Index: 549

Text #9

Max Range: 1.6490. Min Range: -1.6490

Max Act: 1.4773. Min Act: -0.1700

Data Index: 1999576 (Open Web Text)

Max Activating Token Index: 200

Text #10

Max Range: 1.6490. Min Range: -1.6490

Max Act: 1.4716. Min Act: -0.1700

Data Index: 3439064 (Open Web Text)

Max Activating Token Index: 111

Text #11

Max Range: 1.6490. Min Range: -1.6490

Max Act: 1.4707. Min Act: -0.1700

Data Index: 5290637 (Open Web Text)

Max Activating Token Index: 235

Text #12

Max Range: 1.6490. Min Range: -1.6490

Max Act: 1.4653. Min Act: -0.1700

Data Index: 477642 (Open Web Text)

Max Activating Token Index: 96

Text #13

Max Range: 1.6490. Min Range: -1.6490

Max Act: 1.4535. Min Act: -0.1700

Data Index: 6613892 (Open Web Text)

Max Activating Token Index: 202

Text #14

Max Range: 1.6490. Min Range: -1.6490

Max Act: 1.4510. Min Act: -0.1700

Data Index: 434080 (Open Web Text)

Max Activating Token Index: 143

Text #15

Max Range: 1.6490. Min Range: -1.6490

Max Act: 1.4426. Min Act: -0.1700

Data Index: 2919586 (Open Web Text)

Max Activating Token Index: 355

Text #16

Max Range: 1.6490. Min Range: -1.6490

Max Act: 1.4428. Min Act: -0.1700

Data Index: 1333075 (Open Web Text)

Max Activating Token Index: 86

Text #17

Max Range: 1.6490. Min Range: -1.6490

Max Act: 1.4464. Min Act: -0.1700

Data Index: 7682977 (Open Web Text)

Max Activating Token Index: 39

Text #18

Max Range: 1.6490. Min Range: -1.6490

Max Act: 1.4389. Min Act: -0.1700

Data Index: 7976204 (Open Web Text)

Max Activating Token Index: 23

Text #19

Max Range: 1.6490. Min Range: -1.6490

Max Act: 1.4451. Min Act: -0.1700

Data Index: 6308119 (Open Web Text)

Max Activating Token Index: 143