Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3646 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.1685. Min Range: -12.1685
Max Act: 12.1685. Min Act: -0.1700
Data Index: 2405229 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.1685. Min Range: -12.1685
Max Act: 10.8560. Min Act: -0.1700
Data Index: 3546749 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.1685. Min Range: -12.1685
Max Act: 10.7310. Min Act: -0.1700
Data Index: 6739434 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.1685. Min Range: -12.1685
Max Act: 10.7310. Min Act: -0.1700
Data Index: 4108971 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.1685. Min Range: -12.1685
Max Act: 10.6685. Min Act: -0.1700
Data Index: 4890289 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.1685. Min Range: -12.1685
Max Act: 10.6060. Min Act: -0.1700
Data Index: 7173245 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.1685. Min Range: -12.1685
Max Act: 10.4810. Min Act: -0.1700
Data Index: 2405230 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.1685. Min Range: -12.1685
Max Act: 10.4185. Min Act: -0.1700
Data Index: 926102 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.1685. Min Range: -12.1685
Max Act: 10.3560. Min Act: -0.1700
Data Index: 3784755 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.1685. Min Range: -12.1685
Max Act: 10.3560. Min Act: -0.1700
Data Index: 3417751 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.1685. Min Range: -12.1685
Max Act: 10.3560. Min Act: -0.1700
Data Index: 3784749 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.1685. Min Range: -12.1685
Max Act: 10.2310. Min Act: -0.1700
Data Index: 8640010 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.1685. Min Range: -12.1685
Max Act: 10.2935. Min Act: -0.1700
Data Index: 2992002 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.1685. Min Range: -12.1685
Max Act: 10.1685. Min Act: -0.1700
Data Index: 3236180 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.1685. Min Range: -12.1685
Max Act: 10.1685. Min Act: -0.1700
Data Index: 641451 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.1685. Min Range: -12.1685
Max Act: 10.1685. Min Act: -0.1700
Data Index: 1071254 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.1685. Min Range: -12.1685
Max Act: 10.1060. Min Act: -0.1700
Data Index: 268085 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.1685. Min Range: -12.1685
Max Act: 10.1060. Min Act: -0.1700
Data Index: 3627770 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.1685. Min Range: -12.1685
Max Act: 10.1060. Min Act: -0.1700
Data Index: 3546746 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.1685. Min Range: -12.1685
Max Act: 10.1060. Min Act: -0.1700
Data Index: 4741903 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #19