Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2625 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8852. Min Range: -3.8852
Max Act: 3.8852. Min Act: -0.1700
Data Index: 1500047 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8852. Min Range: -3.8852
Max Act: 3.8070. Min Act: -0.1700
Data Index: 7928201 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8852. Min Range: -3.8852
Max Act: 3.7601. Min Act: -0.1700
Data Index: 1785937 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8852. Min Range: -3.8852
Max Act: 3.6663. Min Act: -0.1700
Data Index: 4043825 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8852. Min Range: -3.8852
Max Act: 3.6037. Min Act: -0.1700
Data Index: 3050501 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8852. Min Range: -3.8852
Max Act: 3.5567. Min Act: -0.1700
Data Index: 739439 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8852. Min Range: -3.8852
Max Act: 3.5724. Min Act: -0.1700
Data Index: 764257 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8852. Min Range: -3.8852
Max Act: 3.5411. Min Act: -0.1700
Data Index: 6432168 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8852. Min Range: -3.8852
Max Act: 3.5411. Min Act: -0.1700
Data Index: 8377857 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8852. Min Range: -3.8852
Max Act: 3.5254. Min Act: -0.1700
Data Index: 8227837 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8852. Min Range: -3.8852
Max Act: 3.4941. Min Act: -0.1700
Data Index: 658288 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8852. Min Range: -3.8852
Max Act: 3.4941. Min Act: -0.1700
Data Index: 5497636 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8852. Min Range: -3.8852
Max Act: 3.4941. Min Act: -0.1700
Data Index: 4624554 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8852. Min Range: -3.8852
Max Act: 3.4941. Min Act: -0.1700
Data Index: 3095916 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8852. Min Range: -3.8852
Max Act: 3.4941. Min Act: -0.1700
Data Index: 3462351 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8852. Min Range: -3.8852
Max Act: 3.4471. Min Act: -0.1700
Data Index: 2506723 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8852. Min Range: -3.8852
Max Act: 3.4314. Min Act: -0.1700
Data Index: 8241091 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8852. Min Range: -3.8852
Max Act: 3.4471. Min Act: -0.1700
Data Index: 2535511 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8852. Min Range: -3.8852
Max Act: 3.4471. Min Act: -0.1700
Data Index: 1074386 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8852. Min Range: -3.8852
Max Act: 3.4157. Min Act: -0.1700
Data Index: 252666 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #19