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

Dataset: Open Web Text

Neuron 1801 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: 3.1760. Min Range: -3.1760

Max Act: 3.1646. Min Act: -0.1700

Data Index: 6464799 (Open Web Text)

Max Activating Token Index: 315

Text #1

Max Range: 3.1760. Min Range: -3.1760

Max Act: 3.1581. Min Act: -0.1700

Data Index: 3054682 (Open Web Text)

Max Activating Token Index: 474

Text #2

Max Range: 3.1760. Min Range: -3.1760

Max Act: 3.1491. Min Act: -0.1700

Data Index: 1443652 (Open Web Text)

Max Activating Token Index: 99

Text #3

Max Range: 3.1760. Min Range: -3.1760

Max Act: 3.1760. Min Act: -0.1700

Data Index: 2705903 (Open Web Text)

Max Activating Token Index: 726

Text #4

Max Range: 3.1760. Min Range: -3.1760

Max Act: 3.1585. Min Act: -0.1700

Data Index: 2391922 (Open Web Text)

Max Activating Token Index: 995

Text #5

Max Range: 3.1760. Min Range: -3.1760

Max Act: 3.1571. Min Act: -0.1700

Data Index: 2677334 (Open Web Text)

Max Activating Token Index: 643

Text #6

Max Range: 3.1760. Min Range: -3.1760

Max Act: 3.1338. Min Act: -0.1700

Data Index: 5202056 (Open Web Text)

Max Activating Token Index: 256

Text #7

Max Range: 3.1760. Min Range: -3.1760

Max Act: 3.1232. Min Act: -0.1700

Data Index: 2105433 (Open Web Text)

Max Activating Token Index: 1008

Text #8

Max Range: 3.1760. Min Range: -3.1760

Max Act: 3.1213. Min Act: -0.1700

Data Index: 4698954 (Open Web Text)

Max Activating Token Index: 1004

Text #9

Max Range: 3.1760. Min Range: -3.1760

Max Act: 3.1136. Min Act: -0.1700

Data Index: 1293897 (Open Web Text)

Max Activating Token Index: 930

Text #10

Max Range: 3.1760. Min Range: -3.1760

Max Act: 3.1117. Min Act: -0.1700

Data Index: 773787 (Open Web Text)

Max Activating Token Index: 844

Text #11

Max Range: 3.1760. Min Range: -3.1760

Max Act: 3.1188. Min Act: -0.1700

Data Index: 5494658 (Open Web Text)

Max Activating Token Index: 146

Text #12

Max Range: 3.1760. Min Range: -3.1760

Max Act: 3.1205. Min Act: -0.1700

Data Index: 5484962 (Open Web Text)

Max Activating Token Index: 232

Text #13

Max Range: 3.1760. Min Range: -3.1760

Max Act: 3.0987. Min Act: -0.1700

Data Index: 7907421 (Open Web Text)

Max Activating Token Index: 510

Text #14

Max Range: 3.1760. Min Range: -3.1760

Max Act: 3.1004. Min Act: -0.1700

Data Index: 6727537 (Open Web Text)

Max Activating Token Index: 904

Text #15

Max Range: 3.1760. Min Range: -3.1760

Max Act: 3.1000. Min Act: -0.1700

Data Index: 786148 (Open Web Text)

Max Activating Token Index: 379

Text #16

Max Range: 3.1760. Min Range: -3.1760

Max Act: 3.0981. Min Act: -0.1700

Data Index: 2540975 (Open Web Text)

Max Activating Token Index: 754

Text #17

Max Range: 3.1760. Min Range: -3.1760

Max Act: 3.0814. Min Act: -0.1700

Data Index: 5932601 (Open Web Text)

Max Activating Token Index: 580

Text #18

Max Range: 3.1760. Min Range: -3.1760

Max Act: 3.1070. Min Act: -0.1700

Data Index: 2222894 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 3.1760. Min Range: -3.1760

Max Act: 3.0915. Min Act: -0.1700

Data Index: 3530682 (Open Web Text)

Max Activating Token Index: 327