Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1834 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5743. Min Range: -7.5743
Max Act: 7.5743. Min Act: -0.1700
Data Index: 3338943 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5743. Min Range: -7.5743
Max Act: 7.3868. Min Act: -0.1700
Data Index: 4180879 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5743. Min Range: -7.5743
Max Act: 7.3868. Min Act: -0.1700
Data Index: 3307069 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5743. Min Range: -7.5743
Max Act: 7.2931. Min Act: -0.1700
Data Index: 3545874 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5743. Min Range: -7.5743
Max Act: 7.2618. Min Act: -0.1700
Data Index: 1407482 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5743. Min Range: -7.5743
Max Act: 7.2306. Min Act: -0.1700
Data Index: 5698653 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5743. Min Range: -7.5743
Max Act: 7.1681. Min Act: -0.1700
Data Index: 5341773 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5743. Min Range: -7.5743
Max Act: 7.1681. Min Act: -0.1700
Data Index: 3618287 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5743. Min Range: -7.5743
Max Act: 7.1368. Min Act: -0.1700
Data Index: 7262806 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5743. Min Range: -7.5743
Max Act: 7.1056. Min Act: -0.1700
Data Index: 5778507 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5743. Min Range: -7.5743
Max Act: 7.0743. Min Act: -0.1700
Data Index: 4425880 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5743. Min Range: -7.5743
Max Act: 7.0743. Min Act: -0.1700
Data Index: 5906258 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5743. Min Range: -7.5743
Max Act: 7.0431. Min Act: -0.1700
Data Index: 326622 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5743. Min Range: -7.5743
Max Act: 7.0118. Min Act: -0.1700
Data Index: 4468775 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5743. Min Range: -7.5743
Max Act: 7.0431. Min Act: -0.1700
Data Index: 6475185 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5743. Min Range: -7.5743
Max Act: 7.0118. Min Act: -0.1700
Data Index: 2223038 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5743. Min Range: -7.5743
Max Act: 7.0118. Min Act: -0.1700
Data Index: 952765 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5743. Min Range: -7.5743
Max Act: 7.0118. Min Act: -0.1700
Data Index: 2298099 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5743. Min Range: -7.5743
Max Act: 7.0118. Min Act: -0.1700
Data Index: 2317897 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5743. Min Range: -7.5743
Max Act: 7.0431. Min Act: -0.1700
Data Index: 923284 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #19