Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3609 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5712. Min Range: -7.5712
Max Act: 7.5712. Min Act: -0.1700
Data Index: 3103447 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5712. Min Range: -7.5712
Max Act: 7.4149. Min Act: -0.1700
Data Index: 7366612 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5712. Min Range: -7.5712
Max Act: 7.1649. Min Act: -0.1700
Data Index: 1920611 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5712. Min Range: -7.5712
Max Act: 7.1024. Min Act: -0.1700
Data Index: 3036022 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5712. Min Range: -7.5712
Max Act: 7.0087. Min Act: -0.1700
Data Index: 1527999 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5712. Min Range: -7.5712
Max Act: 6.9774. Min Act: -0.1700
Data Index: 4488289 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5712. Min Range: -7.5712
Max Act: 6.8524. Min Act: -0.1700
Data Index: 8628672 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5712. Min Range: -7.5712
Max Act: 6.8212. Min Act: -0.1700
Data Index: 3043636 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5712. Min Range: -7.5712
Max Act: 6.6649. Min Act: -0.1700
Data Index: 3668921 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5712. Min Range: -7.5712
Max Act: 6.6962. Min Act: -0.1700
Data Index: 8670774 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5712. Min Range: -7.5712
Max Act: 6.6337. Min Act: -0.1700
Data Index: 1642086 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5712. Min Range: -7.5712
Max Act: 6.6024. Min Act: -0.1700
Data Index: 7240887 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5712. Min Range: -7.5712
Max Act: 6.5712. Min Act: -0.1700
Data Index: 4732698 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5712. Min Range: -7.5712
Max Act: 6.5712. Min Act: -0.1700
Data Index: 8310704 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5712. Min Range: -7.5712
Max Act: 6.5399. Min Act: -0.1700
Data Index: 8500597 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5712. Min Range: -7.5712
Max Act: 6.5087. Min Act: -0.1700
Data Index: 8107354 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5712. Min Range: -7.5712
Max Act: 6.5399. Min Act: -0.1700
Data Index: 8465068 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5712. Min Range: -7.5712
Max Act: 6.5087. Min Act: -0.1700
Data Index: 170285 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5712. Min Range: -7.5712
Max Act: 6.4462. Min Act: -0.1700
Data Index: 804584 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5712. Min Range: -7.5712
Max Act: 6.4774. Min Act: -0.1700
Data Index: 1375046 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #19