Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2008 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9522. Min Range: -9.9522
Max Act: 9.9522. Min Act: -0.1700
Data Index: 5140907 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9522. Min Range: -9.9522
Max Act: 9.9522. Min Act: -0.1700
Data Index: 1750084 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9522. Min Range: -9.9522
Max Act: 9.9522. Min Act: -0.1700
Data Index: 2242518 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9522. Min Range: -9.9522
Max Act: 9.8272. Min Act: -0.1700
Data Index: 8770499 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9522. Min Range: -9.9522
Max Act: 9.7022. Min Act: -0.1700
Data Index: 7336692 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9522. Min Range: -9.9522
Max Act: 9.6397. Min Act: -0.1700
Data Index: 1528917 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9522. Min Range: -9.9522
Max Act: 9.6397. Min Act: -0.1700
Data Index: 2570618 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9522. Min Range: -9.9522
Max Act: 9.5772. Min Act: -0.1700
Data Index: 558747 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9522. Min Range: -9.9522
Max Act: 9.5772. Min Act: -0.1700
Data Index: 4783152 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9522. Min Range: -9.9522
Max Act: 9.5772. Min Act: -0.1700
Data Index: 6348001 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9522. Min Range: -9.9522
Max Act: 9.5147. Min Act: -0.1700
Data Index: 2960092 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9522. Min Range: -9.9522
Max Act: 9.5147. Min Act: -0.1700
Data Index: 5736799 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9522. Min Range: -9.9522
Max Act: 9.4522. Min Act: -0.1700
Data Index: 5027099 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9522. Min Range: -9.9522
Max Act: 9.4522. Min Act: -0.1700
Data Index: 10260 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9522. Min Range: -9.9522
Max Act: 9.5147. Min Act: -0.1700
Data Index: 8426873 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9522. Min Range: -9.9522
Max Act: 9.3897. Min Act: -0.1700
Data Index: 54762 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9522. Min Range: -9.9522
Max Act: 9.3897. Min Act: -0.1700
Data Index: 3461120 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9522. Min Range: -9.9522
Max Act: 9.3272. Min Act: -0.1700
Data Index: 133187 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9522. Min Range: -9.9522
Max Act: 9.2647. Min Act: -0.1700
Data Index: 3610299 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9522. Min Range: -9.9522
Max Act: 9.2647. Min Act: -0.1700
Data Index: 1350311 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #19