Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1346 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6564. Min Range: -5.6564
Max Act: 5.6564. Min Act: -0.1700
Data Index: 8499751 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6564. Min Range: -5.6564
Max Act: 5.6251. Min Act: -0.1700
Data Index: 4472116 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6564. Min Range: -5.6564
Max Act: 5.5626. Min Act: -0.1700
Data Index: 3393663 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6564. Min Range: -5.6564
Max Act: 5.4689. Min Act: -0.1700
Data Index: 3870432 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6564. Min Range: -5.6564
Max Act: 5.4689. Min Act: -0.1700
Data Index: 8309916 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6564. Min Range: -5.6564
Max Act: 5.4689. Min Act: -0.1700
Data Index: 7466696 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6564. Min Range: -5.6564
Max Act: 5.4376. Min Act: -0.1700
Data Index: 96168 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6564. Min Range: -5.6564
Max Act: 5.4376. Min Act: -0.1700
Data Index: 847647 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6564. Min Range: -5.6564
Max Act: 5.4064. Min Act: -0.1700
Data Index: 5677493 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6564. Min Range: -5.6564
Max Act: 5.3751. Min Act: -0.1700
Data Index: 4627385 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6564. Min Range: -5.6564
Max Act: 5.3126. Min Act: -0.1700
Data Index: 1749356 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6564. Min Range: -5.6564
Max Act: 5.2814. Min Act: -0.1700
Data Index: 3806699 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6564. Min Range: -5.6564
Max Act: 5.2814. Min Act: -0.1700
Data Index: 6403198 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6564. Min Range: -5.6564
Max Act: 5.2501. Min Act: -0.1700
Data Index: 2296478 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6564. Min Range: -5.6564
Max Act: 5.2501. Min Act: -0.1700
Data Index: 2973738 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6564. Min Range: -5.6564
Max Act: 5.2189. Min Act: -0.1700
Data Index: 2022433 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6564. Min Range: -5.6564
Max Act: 5.2501. Min Act: -0.1700
Data Index: 6995807 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6564. Min Range: -5.6564
Max Act: 5.2501. Min Act: -0.1700
Data Index: 8575558 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6564. Min Range: -5.6564
Max Act: 5.2501. Min Act: -0.1700
Data Index: 2889659 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6564. Min Range: -5.6564
Max Act: 5.2189. Min Act: -0.1700
Data Index: 7346007 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #19