Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5770 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2017. Min Range: -5.2017
Max Act: 5.2017. Min Act: -0.1700
Data Index: 6854181 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2017. Min Range: -5.2017
Max Act: 5.1704. Min Act: -0.1700
Data Index: 4365701 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2017. Min Range: -5.2017
Max Act: 5.1392. Min Act: -0.1700
Data Index: 3392356 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2017. Min Range: -5.2017
Max Act: 5.0767. Min Act: -0.1700
Data Index: 6784511 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2017. Min Range: -5.2017
Max Act: 5.0767. Min Act: -0.1700
Data Index: 8239533 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2017. Min Range: -5.2017
Max Act: 5.0767. Min Act: -0.1700
Data Index: 4528383 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2017. Min Range: -5.2017
Max Act: 5.0454. Min Act: -0.1700
Data Index: 5458110 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2017. Min Range: -5.2017
Max Act: 5.0142. Min Act: -0.1700
Data Index: 6010306 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2017. Min Range: -5.2017
Max Act: 4.9829. Min Act: -0.1700
Data Index: 6839946 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2017. Min Range: -5.2017
Max Act: 4.9829. Min Act: -0.1700
Data Index: 1397562 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2017. Min Range: -5.2017
Max Act: 4.9517. Min Act: -0.1700
Data Index: 5770585 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2017. Min Range: -5.2017
Max Act: 4.9517. Min Act: -0.1700
Data Index: 3000545 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2017. Min Range: -5.2017
Max Act: 4.9204. Min Act: -0.1700
Data Index: 441266 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2017. Min Range: -5.2017
Max Act: 4.9204. Min Act: -0.1700
Data Index: 364123 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2017. Min Range: -5.2017
Max Act: 4.8892. Min Act: -0.1700
Data Index: 1719477 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2017. Min Range: -5.2017
Max Act: 4.9204. Min Act: -0.1700
Data Index: 6876502 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2017. Min Range: -5.2017
Max Act: 4.8892. Min Act: -0.1700
Data Index: 6393841 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2017. Min Range: -5.2017
Max Act: 4.8579. Min Act: -0.1700
Data Index: 6924551 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2017. Min Range: -5.2017
Max Act: 4.8579. Min Act: -0.1700
Data Index: 554394 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2017. Min Range: -5.2017
Max Act: 4.8267. Min Act: -0.1700
Data Index: 6095095 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #19