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

Dataset: Open Web Text

Neuron 2360 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: 0.2531. Min Range: -0.2531

Max Act: 0.2531. Min Act: -0.1697

Data Index: 4836280 (Open Web Text)

Max Activating Token Index: 912

Text #1

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.2423. Min Act: -0.1700

Data Index: 1535508 (Open Web Text)

Max Activating Token Index: 988

Text #2

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.2307. Min Act: -0.1696

Data Index: 908975 (Open Web Text)

Max Activating Token Index: 682

Text #3

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.2387. Min Act: -0.1683

Data Index: 8778673 (Open Web Text)

Max Activating Token Index: 181

Text #4

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.2190. Min Act: -0.1677

Data Index: 2310372 (Open Web Text)

Max Activating Token Index: 430

Text #5

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.2228. Min Act: -0.1699

Data Index: 2725476 (Open Web Text)

Max Activating Token Index: 662

Text #6

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.2092. Min Act: -0.1684

Data Index: 8484181 (Open Web Text)

Max Activating Token Index: 1005

Text #7

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.2130. Min Act: -0.1699

Data Index: 5649441 (Open Web Text)

Max Activating Token Index: 516

Text #8

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.2108. Min Act: -0.1700

Data Index: 7146854 (Open Web Text)

Max Activating Token Index: 752

Text #9

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.2140. Min Act: -0.1695

Data Index: 7339916 (Open Web Text)

Max Activating Token Index: 405

Text #10

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.2070. Min Act: -0.1700

Data Index: 1451392 (Open Web Text)

Max Activating Token Index: 913

Text #11

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.2212. Min Act: -0.1699

Data Index: 1058851 (Open Web Text)

Max Activating Token Index: 957

Text #12

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.2031. Min Act: -0.1697

Data Index: 1026461 (Open Web Text)

Max Activating Token Index: 937

Text #13

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.2124. Min Act: -0.1700

Data Index: 4727458 (Open Web Text)

Max Activating Token Index: 242

Text #14

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.2032. Min Act: -0.1700

Data Index: 3646018 (Open Web Text)

Max Activating Token Index: 95

Text #15

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.1968. Min Act: -0.1700

Data Index: 7384715 (Open Web Text)

Max Activating Token Index: 326

Text #16

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.2024. Min Act: -0.1700

Data Index: 3986265 (Open Web Text)

Max Activating Token Index: 364

Text #17

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.1906. Min Act: -0.1697

Data Index: 1785298 (Open Web Text)

Max Activating Token Index: 334

Text #18

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.1977. Min Act: -0.1700

Data Index: 2287814 (Open Web Text)

Max Activating Token Index: 197

Text #19

Max Range: 0.2531. Min Range: -0.2531

Max Act: 0.1872. Min Act: -0.1698

Data Index: 1256097 (Open Web Text)

Max Activating Token Index: 284