Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3070 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9145. Min Range: -6.9145
Max Act: 6.9145. Min Act: -0.1700
Data Index: 7956416 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9145. Min Range: -6.9145
Max Act: 6.8520. Min Act: -0.1700
Data Index: 7956408 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9145. Min Range: -6.9145
Max Act: 6.6957. Min Act: -0.1700
Data Index: 2372311 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9145. Min Range: -6.9145
Max Act: 6.4770. Min Act: -0.1700
Data Index: 5789149 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9145. Min Range: -6.9145
Max Act: 6.4145. Min Act: -0.1700
Data Index: 4230629 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9145. Min Range: -6.9145
Max Act: 6.4145. Min Act: -0.1700
Data Index: 1618007 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9145. Min Range: -6.9145
Max Act: 6.3520. Min Act: -0.1700
Data Index: 1443559 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9145. Min Range: -6.9145
Max Act: 6.3207. Min Act: -0.1700
Data Index: 6369233 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9145. Min Range: -6.9145
Max Act: 6.2895. Min Act: -0.1700
Data Index: 4114270 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9145. Min Range: -6.9145
Max Act: 6.2895. Min Act: -0.1700
Data Index: 1346764 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9145. Min Range: -6.9145
Max Act: 6.2582. Min Act: -0.1700
Data Index: 1730787 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9145. Min Range: -6.9145
Max Act: 6.2582. Min Act: -0.1700
Data Index: 638885 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9145. Min Range: -6.9145
Max Act: 6.2270. Min Act: -0.1700
Data Index: 6613689 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9145. Min Range: -6.9145
Max Act: 6.2582. Min Act: -0.1700
Data Index: 5461627 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9145. Min Range: -6.9145
Max Act: 6.2582. Min Act: -0.1700
Data Index: 65338 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9145. Min Range: -6.9145
Max Act: 6.2270. Min Act: -0.1700
Data Index: 8588104 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9145. Min Range: -6.9145
Max Act: 6.2270. Min Act: -0.1700
Data Index: 7883748 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9145. Min Range: -6.9145
Max Act: 6.2270. Min Act: -0.1700
Data Index: 5410447 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9145. Min Range: -6.9145
Max Act: 6.1957. Min Act: -0.1700
Data Index: 6785113 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9145. Min Range: -6.9145
Max Act: 6.1957. Min Act: -0.1700
Data Index: 3309609 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #19