Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5045 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2854. Min Range: -8.2854
Max Act: 8.2854. Min Act: -0.1700
Data Index: 1626610 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2854. Min Range: -8.2854
Max Act: 7.2854. Min Act: -0.1700
Data Index: 7197673 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2854. Min Range: -8.2854
Max Act: 7.2854. Min Act: -0.1700
Data Index: 2793247 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2854. Min Range: -8.2854
Max Act: 7.2541. Min Act: -0.1700
Data Index: 2340064 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2854. Min Range: -8.2854
Max Act: 7.1291. Min Act: -0.1700
Data Index: 5045221 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2854. Min Range: -8.2854
Max Act: 7.1291. Min Act: -0.1700
Data Index: 6692001 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2854. Min Range: -8.2854
Max Act: 7.0666. Min Act: -0.1700
Data Index: 8483716 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2854. Min Range: -8.2854
Max Act: 7.0979. Min Act: -0.1700
Data Index: 6019049 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2854. Min Range: -8.2854
Max Act: 7.0041. Min Act: -0.1700
Data Index: 1665121 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2854. Min Range: -8.2854
Max Act: 6.9729. Min Act: -0.1700
Data Index: 3722821 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2854. Min Range: -8.2854
Max Act: 6.9416. Min Act: -0.1700
Data Index: 1889414 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2854. Min Range: -8.2854
Max Act: 6.9416. Min Act: -0.1700
Data Index: 734718 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2854. Min Range: -8.2854
Max Act: 6.9104. Min Act: -0.1700
Data Index: 2235669 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2854. Min Range: -8.2854
Max Act: 6.8791. Min Act: -0.1700
Data Index: 1308873 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2854. Min Range: -8.2854
Max Act: 6.8791. Min Act: -0.1700
Data Index: 1376121 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2854. Min Range: -8.2854
Max Act: 6.8479. Min Act: -0.1700
Data Index: 6383606 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2854. Min Range: -8.2854
Max Act: 6.8479. Min Act: -0.1700
Data Index: 52201 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2854. Min Range: -8.2854
Max Act: 6.8166. Min Act: -0.1700
Data Index: 1619122 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2854. Min Range: -8.2854
Max Act: 6.8166. Min Act: -0.1700
Data Index: 8699119 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2854. Min Range: -8.2854
Max Act: 6.7854. Min Act: -0.1700
Data Index: 83145 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #19