Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4710 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7887. Min Range: -5.7887
Max Act: 5.7887. Min Act: -0.1700
Data Index: 1526771 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7887. Min Range: -5.7887
Max Act: 5.7575. Min Act: -0.1700
Data Index: 7560319 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7887. Min Range: -5.7887
Max Act: 5.7262. Min Act: -0.1700
Data Index: 3349180 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7887. Min Range: -5.7887
Max Act: 5.6325. Min Act: -0.1700
Data Index: 5094654 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7887. Min Range: -5.7887
Max Act: 5.6325. Min Act: -0.1700
Data Index: 80522 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7887. Min Range: -5.7887
Max Act: 5.6325. Min Act: -0.1700
Data Index: 8382084 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7887. Min Range: -5.7887
Max Act: 5.6012. Min Act: -0.1700
Data Index: 8656751 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7887. Min Range: -5.7887
Max Act: 5.6012. Min Act: -0.1700
Data Index: 4628033 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7887. Min Range: -5.7887
Max Act: 5.6012. Min Act: -0.1700
Data Index: 3502619 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7887. Min Range: -5.7887
Max Act: 5.6012. Min Act: -0.1700
Data Index: 6438667 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7887. Min Range: -5.7887
Max Act: 5.6012. Min Act: -0.1700
Data Index: 3788291 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7887. Min Range: -5.7887
Max Act: 5.5700. Min Act: -0.1700
Data Index: 8351787 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7887. Min Range: -5.7887
Max Act: 5.5700. Min Act: -0.1700
Data Index: 2748832 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7887. Min Range: -5.7887
Max Act: 5.5700. Min Act: -0.1700
Data Index: 8351788 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7887. Min Range: -5.7887
Max Act: 5.5700. Min Act: -0.1700
Data Index: 7378494 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7887. Min Range: -5.7887
Max Act: 5.5700. Min Act: -0.1700
Data Index: 7169790 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7887. Min Range: -5.7887
Max Act: 5.5700. Min Act: -0.1700
Data Index: 7169791 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7887. Min Range: -5.7887
Max Act: 5.5387. Min Act: -0.1700
Data Index: 306906 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7887. Min Range: -5.7887
Max Act: 5.5075. Min Act: -0.1700
Data Index: 4108717 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7887. Min Range: -5.7887
Max Act: 5.5075. Min Act: -0.1700
Data Index: 6968724 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #19