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

Dataset: Open Web Text

Neuron 960 in Layer 5

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: 4.6232. Min Range: -4.6232

Max Act: 4.6232. Min Act: -0.1700

Data Index: 1348042 (Open Web Text)

Max Activating Token Index: 510

Text #1

Max Range: 4.6232. Min Range: -4.6232

Max Act: 4.4919. Min Act: -0.1700

Data Index: 2879647 (Open Web Text)

Max Activating Token Index: 650

Text #2

Max Range: 4.6232. Min Range: -4.6232

Max Act: 4.4179. Min Act: -0.1700

Data Index: 4267348 (Open Web Text)

Max Activating Token Index: 47

Text #3

Max Range: 4.6232. Min Range: -4.6232

Max Act: 4.3284. Min Act: -0.1700

Data Index: 1613459 (Open Web Text)

Max Activating Token Index: 44

Text #4

Max Range: 4.6232. Min Range: -4.6232

Max Act: 4.2879. Min Act: -0.1700

Data Index: 7704920 (Open Web Text)

Max Activating Token Index: 744

Text #5

Max Range: 4.6232. Min Range: -4.6232

Max Act: 4.2093. Min Act: -0.1700

Data Index: 5238654 (Open Web Text)

Max Activating Token Index: 567

Text #6

Max Range: 4.6232. Min Range: -4.6232

Max Act: 4.2021. Min Act: -0.1700

Data Index: 4262835 (Open Web Text)

Max Activating Token Index: 190

Text #7

Max Range: 4.6232. Min Range: -4.6232

Max Act: 4.1955. Min Act: -0.1700

Data Index: 445197 (Open Web Text)

Max Activating Token Index: 446

Text #8

Max Range: 4.6232. Min Range: -4.6232

Max Act: 4.1602. Min Act: -0.1700

Data Index: 1984289 (Open Web Text)

Max Activating Token Index: 732

Text #9

Max Range: 4.6232. Min Range: -4.6232

Max Act: 4.1943. Min Act: -0.1700

Data Index: 1921871 (Open Web Text)

Max Activating Token Index: 128

Text #10

Max Range: 4.6232. Min Range: -4.6232

Max Act: 4.1722. Min Act: -0.1700

Data Index: 5249174 (Open Web Text)

Max Activating Token Index: 798

Text #11

Max Range: 4.6232. Min Range: -4.6232

Max Act: 4.1173. Min Act: -0.1700

Data Index: 6973386 (Open Web Text)

Max Activating Token Index: 779

Text #12

Max Range: 4.6232. Min Range: -4.6232

Max Act: 4.1675. Min Act: -0.1700

Data Index: 5690103 (Open Web Text)

Max Activating Token Index: 741

Text #13

Max Range: 4.6232. Min Range: -4.6232

Max Act: 4.1627. Min Act: -0.1700

Data Index: 4647405 (Open Web Text)

Max Activating Token Index: 552

Text #14

Max Range: 4.6232. Min Range: -4.6232

Max Act: 4.1426. Min Act: -0.1700

Data Index: 1983808 (Open Web Text)

Max Activating Token Index: 366

Text #15

Max Range: 4.6232. Min Range: -4.6232

Max Act: 4.1592. Min Act: -0.1700

Data Index: 2885434 (Open Web Text)

Max Activating Token Index: 743

Text #16

Max Range: 4.6232. Min Range: -4.6232

Max Act: 4.1426. Min Act: -0.1700

Data Index: 4187177 (Open Web Text)

Max Activating Token Index: 139

Text #17

Max Range: 4.6232. Min Range: -4.6232

Max Act: 4.1594. Min Act: -0.1700

Data Index: 3394833 (Open Web Text)

Max Activating Token Index: 708

Text #18

Max Range: 4.6232. Min Range: -4.6232

Max Act: 4.1391. Min Act: -0.1700

Data Index: 2984456 (Open Web Text)

Max Activating Token Index: 546

Text #19

Max Range: 4.6232. Min Range: -4.6232

Max Act: 4.1212. Min Act: -0.1700

Data Index: 3025653 (Open Web Text)

Max Activating Token Index: 28