Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1040 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.4042. Min Range: -11.4042
Max Act: 11.4042. Min Act: -0.1700
Data Index: 8309971 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.4042. Min Range: -11.4042
Max Act: 10.9667. Min Act: -0.1700
Data Index: 7530798 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.4042. Min Range: -11.4042
Max Act: 10.7792. Min Act: -0.1700
Data Index: 5775716 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.4042. Min Range: -11.4042
Max Act: 10.8417. Min Act: -0.1700
Data Index: 1637086 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.4042. Min Range: -11.4042
Max Act: 10.6542. Min Act: -0.1700
Data Index: 247413 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.4042. Min Range: -11.4042
Max Act: 10.5917. Min Act: -0.1700
Data Index: 993059 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.4042. Min Range: -11.4042
Max Act: 10.5917. Min Act: -0.1700
Data Index: 5498771 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.4042. Min Range: -11.4042
Max Act: 10.5292. Min Act: -0.1700
Data Index: 351848 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.4042. Min Range: -11.4042
Max Act: 10.5292. Min Act: -0.1700
Data Index: 654739 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.4042. Min Range: -11.4042
Max Act: 10.5292. Min Act: -0.1700
Data Index: 564811 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.4042. Min Range: -11.4042
Max Act: 10.4667. Min Act: -0.1700
Data Index: 8168226 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.4042. Min Range: -11.4042
Max Act: 10.4667. Min Act: -0.1700
Data Index: 7987867 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.4042. Min Range: -11.4042
Max Act: 10.4667. Min Act: -0.1700
Data Index: 1532838 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.4042. Min Range: -11.4042
Max Act: 10.4667. Min Act: -0.1700
Data Index: 993060 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.4042. Min Range: -11.4042
Max Act: 10.4667. Min Act: -0.1700
Data Index: 1727481 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.4042. Min Range: -11.4042
Max Act: 10.4667. Min Act: -0.1700
Data Index: 1017433 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.4042. Min Range: -11.4042
Max Act: 10.4667. Min Act: -0.1700
Data Index: 4510197 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.4042. Min Range: -11.4042
Max Act: 10.4042. Min Act: -0.1700
Data Index: 2771945 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.4042. Min Range: -11.4042
Max Act: 10.4042. Min Act: -0.1700
Data Index: 5764850 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.4042. Min Range: -11.4042
Max Act: 10.4042. Min Act: -0.1700
Data Index: 1637085 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #19