Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3399 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0017. Min Range: -6.0017
Max Act: 6.0017. Min Act: -0.1700
Data Index: 4575708 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0017. Min Range: -6.0017
Max Act: 5.8767. Min Act: -0.1700
Data Index: 3473452 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0017. Min Range: -6.0017
Max Act: 5.8142. Min Act: -0.1700
Data Index: 5078331 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0017. Min Range: -6.0017
Max Act: 5.7830. Min Act: -0.1700
Data Index: 3455198 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0017. Min Range: -6.0017
Max Act: 5.7517. Min Act: -0.1700
Data Index: 3680800 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0017. Min Range: -6.0017
Max Act: 5.6892. Min Act: -0.1700
Data Index: 4187497 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0017. Min Range: -6.0017
Max Act: 5.7517. Min Act: -0.1700
Data Index: 7360015 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0017. Min Range: -6.0017
Max Act: 5.6892. Min Act: -0.1700
Data Index: 7068750 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0017. Min Range: -6.0017
Max Act: 5.6892. Min Act: -0.1700
Data Index: 8639759 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0017. Min Range: -6.0017
Max Act: 5.6580. Min Act: -0.1700
Data Index: 6492509 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0017. Min Range: -6.0017
Max Act: 5.6580. Min Act: -0.1700
Data Index: 1627038 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0017. Min Range: -6.0017
Max Act: 5.5955. Min Act: -0.1700
Data Index: 2306003 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0017. Min Range: -6.0017
Max Act: 5.5955. Min Act: -0.1700
Data Index: 1040470 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0017. Min Range: -6.0017
Max Act: 5.6267. Min Act: -0.1700
Data Index: 8333944 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0017. Min Range: -6.0017
Max Act: 5.5955. Min Act: -0.1700
Data Index: 8302042 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0017. Min Range: -6.0017
Max Act: 5.5642. Min Act: -0.1700
Data Index: 7297993 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0017. Min Range: -6.0017
Max Act: 5.5642. Min Act: -0.1700
Data Index: 1048952 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0017. Min Range: -6.0017
Max Act: 5.5642. Min Act: -0.1700
Data Index: 4238681 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0017. Min Range: -6.0017
Max Act: 5.5330. Min Act: -0.1700
Data Index: 7781919 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0017. Min Range: -6.0017
Max Act: 5.5330. Min Act: -0.1700
Data Index: 5566861 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #19