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

Dataset: Open Web Text

Neuron 2089 in Layer 2

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: 3.8082. Min Range: -3.8082

Max Act: 3.8082. Min Act: -0.1700

Data Index: 7962489 (Open Web Text)

Max Activating Token Index: 431

Text #1

Max Range: 3.8082. Min Range: -3.8082

Max Act: 3.7511. Min Act: -0.1700

Data Index: 1909597 (Open Web Text)

Max Activating Token Index: 7

Text #2

Max Range: 3.8082. Min Range: -3.8082

Max Act: 3.7406. Min Act: -0.1700

Data Index: 7495328 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 3.8082. Min Range: -3.8082

Max Act: 3.7170. Min Act: -0.1700

Data Index: 8470530 (Open Web Text)

Max Activating Token Index: 16

Text #4

Max Range: 3.8082. Min Range: -3.8082

Max Act: 3.6907. Min Act: -0.1700

Data Index: 8117060 (Open Web Text)

Max Activating Token Index: 936

Text #5

Max Range: 3.8082. Min Range: -3.8082

Max Act: 3.7079. Min Act: -0.1700

Data Index: 2128033 (Open Web Text)

Max Activating Token Index: 19

Text #6

Max Range: 3.8082. Min Range: -3.8082

Max Act: 3.7133. Min Act: -0.1700

Data Index: 4677857 (Open Web Text)

Max Activating Token Index: 11

Text #7

Max Range: 3.8082. Min Range: -3.8082

Max Act: 3.6943. Min Act: -0.1700

Data Index: 946088 (Open Web Text)

Max Activating Token Index: 23

Text #8

Max Range: 3.8082. Min Range: -3.8082

Max Act: 3.7139. Min Act: -0.1700

Data Index: 1900253 (Open Web Text)

Max Activating Token Index: 18

Text #9

Max Range: 3.8082. Min Range: -3.8082

Max Act: 3.7092. Min Act: -0.1700

Data Index: 3838319 (Open Web Text)

Max Activating Token Index: 383

Text #10

Max Range: 3.8082. Min Range: -3.8082

Max Act: 3.6808. Min Act: -0.1700

Data Index: 3101732 (Open Web Text)

Max Activating Token Index: 359

Text #11

Max Range: 3.8082. Min Range: -3.8082

Max Act: 3.7070. Min Act: -0.1700

Data Index: 2066251 (Open Web Text)

Max Activating Token Index: 349

Text #12

Max Range: 3.8082. Min Range: -3.8082

Max Act: 3.6906. Min Act: -0.1700

Data Index: 5001018 (Open Web Text)

Max Activating Token Index: 59

Text #13

Max Range: 3.8082. Min Range: -3.8082

Max Act: 3.6928. Min Act: -0.1700

Data Index: 5761735 (Open Web Text)

Max Activating Token Index: 15

Text #14

Max Range: 3.8082. Min Range: -3.8082

Max Act: 3.6859. Min Act: -0.1700

Data Index: 3073606 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 3.8082. Min Range: -3.8082

Max Act: 3.6686. Min Act: -0.1700

Data Index: 3175093 (Open Web Text)

Max Activating Token Index: 834

Text #16

Max Range: 3.8082. Min Range: -3.8082

Max Act: 3.7196. Min Act: -0.1700

Data Index: 3645364 (Open Web Text)

Max Activating Token Index: 798

Text #17

Max Range: 3.8082. Min Range: -3.8082

Max Act: 3.6714. Min Act: -0.1700

Data Index: 6236556 (Open Web Text)

Max Activating Token Index: 28

Text #18

Max Range: 3.8082. Min Range: -3.8082

Max Act: 3.6676. Min Act: -0.1700

Data Index: 3459572 (Open Web Text)

Max Activating Token Index: 13

Text #19

Max Range: 3.8082. Min Range: -3.8082

Max Act: 3.6376. Min Act: -0.1700

Data Index: 6456725 (Open Web Text)

Max Activating Token Index: 379