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

Dataset: Open Web Text

Neuron 1827 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: 3.1853. Min Range: -3.1853

Max Act: 3.1853. Min Act: -0.1700

Data Index: 8556106 (Open Web Text)

Max Activating Token Index: 381

Text #1

Max Range: 3.1853. Min Range: -3.1853

Max Act: 3.1776. Min Act: -0.1700

Data Index: 1709660 (Open Web Text)

Max Activating Token Index: 111

Text #2

Max Range: 3.1853. Min Range: -3.1853

Max Act: 3.1828. Min Act: -0.1700

Data Index: 6269599 (Open Web Text)

Max Activating Token Index: 846

Text #3

Max Range: 3.1853. Min Range: -3.1853

Max Act: 3.1343. Min Act: -0.1700

Data Index: 5933007 (Open Web Text)

Max Activating Token Index: 760

Text #4

Max Range: 3.1853. Min Range: -3.1853

Max Act: 3.1439. Min Act: -0.1700

Data Index: 6213668 (Open Web Text)

Max Activating Token Index: 687

Text #5

Max Range: 3.1853. Min Range: -3.1853

Max Act: 3.1458. Min Act: -0.1700

Data Index: 2023760 (Open Web Text)

Max Activating Token Index: 259

Text #6

Max Range: 3.1853. Min Range: -3.1853

Max Act: 3.1180. Min Act: -0.1700

Data Index: 4214967 (Open Web Text)

Max Activating Token Index: 430

Text #7

Max Range: 3.1853. Min Range: -3.1853

Max Act: 3.1242. Min Act: -0.1700

Data Index: 5168371 (Open Web Text)

Max Activating Token Index: 202

Text #8

Max Range: 3.1853. Min Range: -3.1853

Max Act: 3.1346. Min Act: -0.1700

Data Index: 3001560 (Open Web Text)

Max Activating Token Index: 132

Text #9

Max Range: 3.1853. Min Range: -3.1853

Max Act: 3.1064. Min Act: -0.1700

Data Index: 7936576 (Open Web Text)

Max Activating Token Index: 345

Text #10

Max Range: 3.1853. Min Range: -3.1853

Max Act: 3.1035. Min Act: -0.1700

Data Index: 5001512 (Open Web Text)

Max Activating Token Index: 354

Text #11

Max Range: 3.1853. Min Range: -3.1853

Max Act: 3.1126. Min Act: -0.1700

Data Index: 2243734 (Open Web Text)

Max Activating Token Index: 517

Text #12

Max Range: 3.1853. Min Range: -3.1853

Max Act: 3.1250. Min Act: -0.1700

Data Index: 7712242 (Open Web Text)

Max Activating Token Index: 178

Text #13

Max Range: 3.1853. Min Range: -3.1853

Max Act: 3.1089. Min Act: -0.1700

Data Index: 7794343 (Open Web Text)

Max Activating Token Index: 148

Text #14

Max Range: 3.1853. Min Range: -3.1853

Max Act: 3.1027. Min Act: -0.1700

Data Index: 5027555 (Open Web Text)

Max Activating Token Index: 524

Text #15

Max Range: 3.1853. Min Range: -3.1853

Max Act: 3.1060. Min Act: -0.1700

Data Index: 7242685 (Open Web Text)

Max Activating Token Index: 635

Text #16

Max Range: 3.1853. Min Range: -3.1853

Max Act: 3.1028. Min Act: -0.1700

Data Index: 222789 (Open Web Text)

Max Activating Token Index: 573

Text #17

Max Range: 3.1853. Min Range: -3.1853

Max Act: 3.0842. Min Act: -0.1700

Data Index: 1401924 (Open Web Text)

Max Activating Token Index: 64

Text #18

Max Range: 3.1853. Min Range: -3.1853

Max Act: 3.0923. Min Act: -0.1700

Data Index: 7517635 (Open Web Text)

Max Activating Token Index: 287

Text #19

Max Range: 3.1853. Min Range: -3.1853

Max Act: 3.1004. Min Act: -0.1700

Data Index: 4903777 (Open Web Text)

Max Activating Token Index: 997