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

Dataset: Open Web Text

Neuron 2685 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: 4.8848. Min Range: -4.8848

Max Act: 4.8690. Min Act: -0.1700

Data Index: 537630 (Open Web Text)

Max Activating Token Index: 238

Text #1

Max Range: 4.8848. Min Range: -4.8848

Max Act: 4.8848. Min Act: -0.1700

Data Index: 7766124 (Open Web Text)

Max Activating Token Index: 280

Text #2

Max Range: 4.8848. Min Range: -4.8848

Max Act: 4.8556. Min Act: -0.1700

Data Index: 6559406 (Open Web Text)

Max Activating Token Index: 124

Text #3

Max Range: 4.8848. Min Range: -4.8848

Max Act: 4.7959. Min Act: -0.1700

Data Index: 479346 (Open Web Text)

Max Activating Token Index: 264

Text #4

Max Range: 4.8848. Min Range: -4.8848

Max Act: 4.7856. Min Act: -0.1700

Data Index: 4232645 (Open Web Text)

Max Activating Token Index: 722

Text #5

Max Range: 4.8848. Min Range: -4.8848

Max Act: 4.8236. Min Act: -0.1700

Data Index: 1435900 (Open Web Text)

Max Activating Token Index: 17

Text #6

Max Range: 4.8848. Min Range: -4.8848

Max Act: 4.7830. Min Act: -0.1700

Data Index: 2804249 (Open Web Text)

Max Activating Token Index: 354

Text #7

Max Range: 4.8848. Min Range: -4.8848

Max Act: 4.8291. Min Act: -0.1700

Data Index: 4366595 (Open Web Text)

Max Activating Token Index: 639

Text #8

Max Range: 4.8848. Min Range: -4.8848

Max Act: 4.8446. Min Act: -0.1700

Data Index: 2014841 (Open Web Text)

Max Activating Token Index: 400

Text #9

Max Range: 4.8848. Min Range: -4.8848

Max Act: 4.8214. Min Act: -0.1700

Data Index: 1703742 (Open Web Text)

Max Activating Token Index: 31

Text #10

Max Range: 4.8848. Min Range: -4.8848

Max Act: 4.8063. Min Act: -0.1700

Data Index: 6737217 (Open Web Text)

Max Activating Token Index: 400

Text #11

Max Range: 4.8848. Min Range: -4.8848

Max Act: 4.7742. Min Act: -0.1700

Data Index: 7024871 (Open Web Text)

Max Activating Token Index: 528

Text #12

Max Range: 4.8848. Min Range: -4.8848

Max Act: 4.7855. Min Act: -0.1700

Data Index: 7607921 (Open Web Text)

Max Activating Token Index: 384

Text #13

Max Range: 4.8848. Min Range: -4.8848

Max Act: 4.7885. Min Act: -0.1700

Data Index: 4692023 (Open Web Text)

Max Activating Token Index: 50

Text #14

Max Range: 4.8848. Min Range: -4.8848

Max Act: 4.7745. Min Act: -0.1700

Data Index: 486414 (Open Web Text)

Max Activating Token Index: 293

Text #15

Max Range: 4.8848. Min Range: -4.8848

Max Act: 4.8140. Min Act: -0.1700

Data Index: 1084330 (Open Web Text)

Max Activating Token Index: 391

Text #16

Max Range: 4.8848. Min Range: -4.8848

Max Act: 4.7621. Min Act: -0.1700

Data Index: 5460386 (Open Web Text)

Max Activating Token Index: 771

Text #17

Max Range: 4.8848. Min Range: -4.8848

Max Act: 4.8124. Min Act: -0.1700

Data Index: 4172841 (Open Web Text)

Max Activating Token Index: 987

Text #18

Max Range: 4.8848. Min Range: -4.8848

Max Act: 4.7831. Min Act: -0.1700

Data Index: 3399627 (Open Web Text)

Max Activating Token Index: 627

Text #19

Max Range: 4.8848. Min Range: -4.8848

Max Act: 4.7630. Min Act: -0.1700

Data Index: 18779 (Open Web Text)

Max Activating Token Index: 246