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

Dataset: Open Web Text

Neuron 2979 in Layer 4

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: 4.5414. Min Range: -4.5414

Max Act: 4.5414. Min Act: -0.1700

Data Index: 1801209 (Open Web Text)

Max Activating Token Index: 213

Text #1

Max Range: 4.5414. Min Range: -4.5414

Max Act: 4.3689. Min Act: -0.1700

Data Index: 6608680 (Open Web Text)

Max Activating Token Index: 84

Text #2

Max Range: 4.5414. Min Range: -4.5414

Max Act: 4.3391. Min Act: -0.1700

Data Index: 8130330 (Open Web Text)

Max Activating Token Index: 58

Text #3

Max Range: 4.5414. Min Range: -4.5414

Max Act: 4.3217. Min Act: -0.1700

Data Index: 1095106 (Open Web Text)

Max Activating Token Index: 132

Text #4

Max Range: 4.5414. Min Range: -4.5414

Max Act: 4.3387. Min Act: -0.1700

Data Index: 5869635 (Open Web Text)

Max Activating Token Index: 383

Text #5

Max Range: 4.5414. Min Range: -4.5414

Max Act: 4.2879. Min Act: -0.1700

Data Index: 7048765 (Open Web Text)

Max Activating Token Index: 819

Text #6

Max Range: 4.5414. Min Range: -4.5414

Max Act: 4.2643. Min Act: -0.1700

Data Index: 8644864 (Open Web Text)

Max Activating Token Index: 577

Text #7

Max Range: 4.5414. Min Range: -4.5414

Max Act: 4.3164. Min Act: -0.1700

Data Index: 443731 (Open Web Text)

Max Activating Token Index: 550

Text #8

Max Range: 4.5414. Min Range: -4.5414

Max Act: 4.3048. Min Act: -0.1700

Data Index: 7462204 (Open Web Text)

Max Activating Token Index: 344

Text #9

Max Range: 4.5414. Min Range: -4.5414

Max Act: 4.2604. Min Act: -0.1700

Data Index: 1495608 (Open Web Text)

Max Activating Token Index: 391

Text #10

Max Range: 4.5414. Min Range: -4.5414

Max Act: 4.2299. Min Act: -0.1700

Data Index: 1000203 (Open Web Text)

Max Activating Token Index: 204

Text #11

Max Range: 4.5414. Min Range: -4.5414

Max Act: 4.2231. Min Act: -0.1700

Data Index: 2669095 (Open Web Text)

Max Activating Token Index: 512

Text #12

Max Range: 4.5414. Min Range: -4.5414

Max Act: 4.2619. Min Act: -0.1700

Data Index: 4227149 (Open Web Text)

Max Activating Token Index: 797

Text #13

Max Range: 4.5414. Min Range: -4.5414

Max Act: 4.2343. Min Act: -0.1700

Data Index: 7095758 (Open Web Text)

Max Activating Token Index: 409

Text #14

Max Range: 4.5414. Min Range: -4.5414

Max Act: 4.2198. Min Act: -0.1700

Data Index: 3138064 (Open Web Text)

Max Activating Token Index: 582

Text #15

Max Range: 4.5414. Min Range: -4.5414

Max Act: 4.2577. Min Act: -0.1700

Data Index: 4044261 (Open Web Text)

Max Activating Token Index: 51

Text #16

Max Range: 4.5414. Min Range: -4.5414

Max Act: 4.2418. Min Act: -0.1700

Data Index: 6478254 (Open Web Text)

Max Activating Token Index: 726

Text #17

Max Range: 4.5414. Min Range: -4.5414

Max Act: 4.2109. Min Act: -0.1700

Data Index: 4363359 (Open Web Text)

Max Activating Token Index: 645

Text #18

Max Range: 4.5414. Min Range: -4.5414

Max Act: 4.2170. Min Act: -0.1700

Data Index: 4953472 (Open Web Text)

Max Activating Token Index: 249

Text #19

Max Range: 4.5414. Min Range: -4.5414

Max Act: 4.2074. Min Act: -0.1700

Data Index: 4846327 (Open Web Text)

Max Activating Token Index: 388