Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1572 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9311. Min Range: -5.9311
Max Act: 5.9311. Min Act: -0.1700
Data Index: 5018088 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9311. Min Range: -5.9311
Max Act: 5.7436. Min Act: -0.1700
Data Index: 8180372 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9311. Min Range: -5.9311
Max Act: 5.7436. Min Act: -0.1700
Data Index: 7174787 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9311. Min Range: -5.9311
Max Act: 5.7123. Min Act: -0.1700
Data Index: 1075514 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9311. Min Range: -5.9311
Max Act: 5.7123. Min Act: -0.1700
Data Index: 6577460 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9311. Min Range: -5.9311
Max Act: 5.6811. Min Act: -0.1700
Data Index: 2406985 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9311. Min Range: -5.9311
Max Act: 5.6811. Min Act: -0.1700
Data Index: 6565459 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9311. Min Range: -5.9311
Max Act: 5.6186. Min Act: -0.1700
Data Index: 2905671 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9311. Min Range: -5.9311
Max Act: 5.6498. Min Act: -0.1700
Data Index: 3142226 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9311. Min Range: -5.9311
Max Act: 5.6186. Min Act: -0.1700
Data Index: 5158390 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9311. Min Range: -5.9311
Max Act: 5.6186. Min Act: -0.1700
Data Index: 1469882 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9311. Min Range: -5.9311
Max Act: 5.5873. Min Act: -0.1700
Data Index: 5018102 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9311. Min Range: -5.9311
Max Act: 5.5873. Min Act: -0.1700
Data Index: 6107267 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9311. Min Range: -5.9311
Max Act: 5.5873. Min Act: -0.1700
Data Index: 7176205 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9311. Min Range: -5.9311
Max Act: 5.5561. Min Act: -0.1700
Data Index: 2565569 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9311. Min Range: -5.9311
Max Act: 5.5248. Min Act: -0.1700
Data Index: 5291936 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9311. Min Range: -5.9311
Max Act: 5.5248. Min Act: -0.1700
Data Index: 4623702 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9311. Min Range: -5.9311
Max Act: 5.5248. Min Act: -0.1700
Data Index: 2652579 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9311. Min Range: -5.9311
Max Act: 5.5248. Min Act: -0.1700
Data Index: 3969710 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9311. Min Range: -5.9311
Max Act: 5.5248. Min Act: -0.1700
Data Index: 3930200 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #19