Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4376 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.0245. Min Range: -6.0245
Max Act: 6.0245. Min Act: -0.1700
Data Index: 4171333 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0245. Min Range: -6.0245
Max Act: 6.0245. Min Act: -0.1700
Data Index: 8789291 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0245. Min Range: -6.0245
Max Act: 5.9307. Min Act: -0.1700
Data Index: 2493602 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0245. Min Range: -6.0245
Max Act: 5.8682. Min Act: -0.1700
Data Index: 6267411 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0245. Min Range: -6.0245
Max Act: 5.8057. Min Act: -0.1700
Data Index: 3307356 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0245. Min Range: -6.0245
Max Act: 5.7745. Min Act: -0.1700
Data Index: 4340184 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0245. Min Range: -6.0245
Max Act: 5.6807. Min Act: -0.1700
Data Index: 1023970 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0245. Min Range: -6.0245
Max Act: 5.5870. Min Act: -0.1700
Data Index: 1279872 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0245. Min Range: -6.0245
Max Act: 5.5870. Min Act: -0.1700
Data Index: 4170745 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0245. Min Range: -6.0245
Max Act: 5.6182. Min Act: -0.1700
Data Index: 6411284 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0245. Min Range: -6.0245
Max Act: 5.5557. Min Act: -0.1700
Data Index: 1496277 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0245. Min Range: -6.0245
Max Act: 5.5245. Min Act: -0.1700
Data Index: 7558059 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0245. Min Range: -6.0245
Max Act: 5.5245. Min Act: -0.1700
Data Index: 7526772 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0245. Min Range: -6.0245
Max Act: 5.4932. Min Act: -0.1700
Data Index: 232546 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0245. Min Range: -6.0245
Max Act: 5.4932. Min Act: -0.1700
Data Index: 8537586 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0245. Min Range: -6.0245
Max Act: 5.4932. Min Act: -0.1700
Data Index: 6319968 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0245. Min Range: -6.0245
Max Act: 5.4620. Min Act: -0.1700
Data Index: 5799360 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0245. Min Range: -6.0245
Max Act: 5.4932. Min Act: -0.1700
Data Index: 1818029 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0245. Min Range: -6.0245
Max Act: 5.4932. Min Act: -0.1700
Data Index: 4688355 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0245. Min Range: -6.0245
Max Act: 5.4307. Min Act: -0.1700
Data Index: 1009722 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #19