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

Dataset: Open Web Text

Neuron 384 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: 3.4735. Min Range: -3.4735

Max Act: 3.4735. Min Act: -0.1700

Data Index: 2053868 (Open Web Text)

Max Activating Token Index: 662

Text #1

Max Range: 3.4735. Min Range: -3.4735

Max Act: 3.2456. Min Act: -0.1700

Data Index: 4364855 (Open Web Text)

Max Activating Token Index: 538

Text #2

Max Range: 3.4735. Min Range: -3.4735

Max Act: 3.2621. Min Act: -0.1700

Data Index: 8303553 (Open Web Text)

Max Activating Token Index: 617

Text #3

Max Range: 3.4735. Min Range: -3.4735

Max Act: 3.2375. Min Act: -0.1700

Data Index: 1270246 (Open Web Text)

Max Activating Token Index: 699

Text #4

Max Range: 3.4735. Min Range: -3.4735

Max Act: 3.2214. Min Act: -0.1700

Data Index: 2496141 (Open Web Text)

Max Activating Token Index: 347

Text #5

Max Range: 3.4735. Min Range: -3.4735

Max Act: 3.1813. Min Act: -0.1700

Data Index: 6700964 (Open Web Text)

Max Activating Token Index: 560

Text #6

Max Range: 3.4735. Min Range: -3.4735

Max Act: 3.1695. Min Act: -0.1700

Data Index: 3707043 (Open Web Text)

Max Activating Token Index: 582

Text #7

Max Range: 3.4735. Min Range: -3.4735

Max Act: 3.1596. Min Act: -0.1700

Data Index: 4872287 (Open Web Text)

Max Activating Token Index: 103

Text #8

Max Range: 3.4735. Min Range: -3.4735

Max Act: 3.1578. Min Act: -0.1700

Data Index: 1687444 (Open Web Text)

Max Activating Token Index: 385

Text #9

Max Range: 3.4735. Min Range: -3.4735

Max Act: 3.1252. Min Act: -0.1696

Data Index: 4415135 (Open Web Text)

Max Activating Token Index: 73

Text #10

Max Range: 3.4735. Min Range: -3.4735

Max Act: 3.1065. Min Act: -0.1700

Data Index: 3300818 (Open Web Text)

Max Activating Token Index: 784

Text #11

Max Range: 3.4735. Min Range: -3.4735

Max Act: 3.1231. Min Act: -0.1700

Data Index: 8484991 (Open Web Text)

Max Activating Token Index: 151

Text #12

Max Range: 3.4735. Min Range: -3.4735

Max Act: 3.1101. Min Act: -0.1700

Data Index: 5367210 (Open Web Text)

Max Activating Token Index: 408

Text #13

Max Range: 3.4735. Min Range: -3.4735

Max Act: 3.0773. Min Act: -0.1700

Data Index: 6647917 (Open Web Text)

Max Activating Token Index: 835

Text #14

Max Range: 3.4735. Min Range: -3.4735

Max Act: 3.0782. Min Act: -0.1700

Data Index: 8048087 (Open Web Text)

Max Activating Token Index: 441

Text #15

Max Range: 3.4735. Min Range: -3.4735

Max Act: 3.0831. Min Act: -0.1700

Data Index: 3916148 (Open Web Text)

Max Activating Token Index: 356

Text #16

Max Range: 3.4735. Min Range: -3.4735

Max Act: 3.0782. Min Act: -0.1700

Data Index: 372893 (Open Web Text)

Max Activating Token Index: 414

Text #17

Max Range: 3.4735. Min Range: -3.4735

Max Act: 3.0913. Min Act: -0.1700

Data Index: 4657954 (Open Web Text)

Max Activating Token Index: 813

Text #18

Max Range: 3.4735. Min Range: -3.4735

Max Act: 3.0766. Min Act: -0.1700

Data Index: 3607412 (Open Web Text)

Max Activating Token Index: 611

Text #19

Max Range: 3.4735. Min Range: -3.4735

Max Act: 3.0783. Min Act: -0.1700

Data Index: 7941499 (Open Web Text)

Max Activating Token Index: 961