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

Dataset: Open Web Text

Neuron 2346 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: 4.7271. Min Range: -4.7271

Max Act: 4.7271. Min Act: -0.1700

Data Index: 6917027 (Open Web Text)

Max Activating Token Index: 715

Text #1

Max Range: 4.7271. Min Range: -4.7271

Max Act: 4.6534. Min Act: -0.1700

Data Index: 1013407 (Open Web Text)

Max Activating Token Index: 470

Text #2

Max Range: 4.7271. Min Range: -4.7271

Max Act: 4.6032. Min Act: -0.1700

Data Index: 8062612 (Open Web Text)

Max Activating Token Index: 174

Text #3

Max Range: 4.7271. Min Range: -4.7271

Max Act: 4.5589. Min Act: -0.1700

Data Index: 5260845 (Open Web Text)

Max Activating Token Index: 465

Text #4

Max Range: 4.7271. Min Range: -4.7271

Max Act: 4.4911. Min Act: -0.1700

Data Index: 4350085 (Open Web Text)

Max Activating Token Index: 502

Text #5

Max Range: 4.7271. Min Range: -4.7271

Max Act: 4.4875. Min Act: -0.1700

Data Index: 7337565 (Open Web Text)

Max Activating Token Index: 927

Text #6

Max Range: 4.7271. Min Range: -4.7271

Max Act: 4.5175. Min Act: -0.1700

Data Index: 3333280 (Open Web Text)

Max Activating Token Index: 687

Text #7

Max Range: 4.7271. Min Range: -4.7271

Max Act: 4.4525. Min Act: -0.1700

Data Index: 4875681 (Open Web Text)

Max Activating Token Index: 855

Text #8

Max Range: 4.7271. Min Range: -4.7271

Max Act: 4.4730. Min Act: -0.1700

Data Index: 180290 (Open Web Text)

Max Activating Token Index: 220

Text #9

Max Range: 4.7271. Min Range: -4.7271

Max Act: 4.4144. Min Act: -0.1700

Data Index: 8441713 (Open Web Text)

Max Activating Token Index: 670

Text #10

Max Range: 4.7271. Min Range: -4.7271

Max Act: 4.4069. Min Act: -0.1700

Data Index: 2627070 (Open Web Text)

Max Activating Token Index: 232

Text #11

Max Range: 4.7271. Min Range: -4.7271

Max Act: 4.4253. Min Act: -0.1700

Data Index: 297996 (Open Web Text)

Max Activating Token Index: 137

Text #12

Max Range: 4.7271. Min Range: -4.7271

Max Act: 4.4086. Min Act: -0.1700

Data Index: 588253 (Open Web Text)

Max Activating Token Index: 371

Text #13

Max Range: 4.7271. Min Range: -4.7271

Max Act: 4.3941. Min Act: -0.1700

Data Index: 2099927 (Open Web Text)

Max Activating Token Index: 496

Text #14

Max Range: 4.7271. Min Range: -4.7271

Max Act: 4.4043. Min Act: -0.1700

Data Index: 1831792 (Open Web Text)

Max Activating Token Index: 988

Text #15

Max Range: 4.7271. Min Range: -4.7271

Max Act: 4.3838. Min Act: -0.1700

Data Index: 3531873 (Open Web Text)

Max Activating Token Index: 978

Text #16

Max Range: 4.7271. Min Range: -4.7271

Max Act: 4.3500. Min Act: -0.1700

Data Index: 2464533 (Open Web Text)

Max Activating Token Index: 750

Text #17

Max Range: 4.7271. Min Range: -4.7271

Max Act: 4.3439. Min Act: -0.1700

Data Index: 6056126 (Open Web Text)

Max Activating Token Index: 960

Text #18

Max Range: 4.7271. Min Range: -4.7271

Max Act: 4.3718. Min Act: -0.1700

Data Index: 6578547 (Open Web Text)

Max Activating Token Index: 641

Text #19

Max Range: 4.7271. Min Range: -4.7271

Max Act: 4.3885. Min Act: -0.1700

Data Index: 6891624 (Open Web Text)

Max Activating Token Index: 594