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

Dataset: Open Web Text

Neuron 2461 in Layer 6

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: 4.1117. Min Range: -4.1117

Max Act: 4.1117. Min Act: -0.1700

Data Index: 1923922 (Open Web Text)

Max Activating Token Index: 552

Text #1

Max Range: 4.1117. Min Range: -4.1117

Max Act: 3.8427. Min Act: -0.1700

Data Index: 6655066 (Open Web Text)

Max Activating Token Index: 974

Text #2

Max Range: 4.1117. Min Range: -4.1117

Max Act: 3.8376. Min Act: -0.1700

Data Index: 4719007 (Open Web Text)

Max Activating Token Index: 602

Text #3

Max Range: 4.1117. Min Range: -4.1117

Max Act: 3.7514. Min Act: -0.1700

Data Index: 7942294 (Open Web Text)

Max Activating Token Index: 685

Text #4

Max Range: 4.1117. Min Range: -4.1117

Max Act: 3.7299. Min Act: -0.1700

Data Index: 1973 (Open Web Text)

Max Activating Token Index: 726

Text #5

Max Range: 4.1117. Min Range: -4.1117

Max Act: 3.7112. Min Act: -0.1700

Data Index: 2446506 (Open Web Text)

Max Activating Token Index: 710

Text #6

Max Range: 4.1117. Min Range: -4.1117

Max Act: 3.7097. Min Act: -0.1700

Data Index: 8113843 (Open Web Text)

Max Activating Token Index: 190

Text #7

Max Range: 4.1117. Min Range: -4.1117

Max Act: 3.6792. Min Act: -0.1700

Data Index: 7480196 (Open Web Text)

Max Activating Token Index: 843

Text #8

Max Range: 4.1117. Min Range: -4.1117

Max Act: 3.6752. Min Act: -0.1700

Data Index: 2236931 (Open Web Text)

Max Activating Token Index: 739

Text #9

Max Range: 4.1117. Min Range: -4.1117

Max Act: 3.6810. Min Act: -0.1700

Data Index: 3446570 (Open Web Text)

Max Activating Token Index: 274

Text #10

Max Range: 4.1117. Min Range: -4.1117

Max Act: 3.6667. Min Act: -0.1700

Data Index: 1938310 (Open Web Text)

Max Activating Token Index: 653

Text #11

Max Range: 4.1117. Min Range: -4.1117

Max Act: 3.6445. Min Act: -0.1700

Data Index: 6322051 (Open Web Text)

Max Activating Token Index: 415

Text #12

Max Range: 4.1117. Min Range: -4.1117

Max Act: 3.6336. Min Act: -0.1700

Data Index: 2392232 (Open Web Text)

Max Activating Token Index: 270

Text #13

Max Range: 4.1117. Min Range: -4.1117

Max Act: 3.6121. Min Act: -0.1700

Data Index: 2715462 (Open Web Text)

Max Activating Token Index: 601

Text #14

Max Range: 4.1117. Min Range: -4.1117

Max Act: 3.6266. Min Act: -0.1700

Data Index: 3273216 (Open Web Text)

Max Activating Token Index: 69

Text #15

Max Range: 4.1117. Min Range: -4.1117

Max Act: 3.5917. Min Act: -0.1700

Data Index: 2293031 (Open Web Text)

Max Activating Token Index: 634

Text #16

Max Range: 4.1117. Min Range: -4.1117

Max Act: 3.5913. Min Act: -0.1700

Data Index: 8140789 (Open Web Text)

Max Activating Token Index: 418

Text #17

Max Range: 4.1117. Min Range: -4.1117

Max Act: 3.5994. Min Act: -0.1700

Data Index: 1709058 (Open Web Text)

Max Activating Token Index: 1015

Text #18

Max Range: 4.1117. Min Range: -4.1117

Max Act: 3.5973. Min Act: -0.1700

Data Index: 283202 (Open Web Text)

Max Activating Token Index: 669

Text #19

Max Range: 4.1117. Min Range: -4.1117

Max Act: 3.6001. Min Act: -0.1700

Data Index: 8476941 (Open Web Text)

Max Activating Token Index: 881