Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2855 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2752. Min Range: -4.2752
Max Act: 4.2440. Min Act: -0.1700
Data Index: 4561168 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2752. Min Range: -4.2752
Max Act: 4.2752. Min Act: -0.1700
Data Index: 7521937 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2752. Min Range: -4.2752
Max Act: 4.2127. Min Act: -0.1700
Data Index: 2301163 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2752. Min Range: -4.2752
Max Act: 4.2127. Min Act: -0.1700
Data Index: 2926835 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2752. Min Range: -4.2752
Max Act: 4.1815. Min Act: -0.1700
Data Index: 2704236 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2752. Min Range: -4.2752
Max Act: 4.1815. Min Act: -0.1700
Data Index: 26362 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2752. Min Range: -4.2752
Max Act: 4.1815. Min Act: -0.1700
Data Index: 4741092 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2752. Min Range: -4.2752
Max Act: 4.1815. Min Act: -0.1700
Data Index: 4711392 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2752. Min Range: -4.2752
Max Act: 4.1815. Min Act: -0.1700
Data Index: 4655957 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2752. Min Range: -4.2752
Max Act: 4.1502. Min Act: -0.1700
Data Index: 7832045 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2752. Min Range: -4.2752
Max Act: 4.1815. Min Act: -0.1700
Data Index: 187448 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2752. Min Range: -4.2752
Max Act: 4.1502. Min Act: -0.1700
Data Index: 7872630 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2752. Min Range: -4.2752
Max Act: 4.1502. Min Act: -0.1700
Data Index: 5351989 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2752. Min Range: -4.2752
Max Act: 4.1502. Min Act: -0.1700
Data Index: 1611637 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2752. Min Range: -4.2752
Max Act: 4.1502. Min Act: -0.1700
Data Index: 7246371 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2752. Min Range: -4.2752
Max Act: 4.1502. Min Act: -0.1700
Data Index: 7124192 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2752. Min Range: -4.2752
Max Act: 4.1190. Min Act: -0.1700
Data Index: 55240 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2752. Min Range: -4.2752
Max Act: 4.1190. Min Act: -0.1700
Data Index: 666879 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2752. Min Range: -4.2752
Max Act: 4.1190. Min Act: -0.1700
Data Index: 964067 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2752. Min Range: -4.2752
Max Act: 4.0877. Min Act: -0.1700
Data Index: 7063878 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #19