Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3744 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5962. Min Range: -8.5962
Max Act: 8.5962. Min Act: -0.1700
Data Index: 5028999 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5962. Min Range: -8.5962
Max Act: 8.4712. Min Act: -0.1700
Data Index: 1482249 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5962. Min Range: -8.5962
Max Act: 8.4087. Min Act: -0.1700
Data Index: 8606403 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5962. Min Range: -8.5962
Max Act: 8.4087. Min Act: -0.1700
Data Index: 7178948 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5962. Min Range: -8.5962
Max Act: 8.4087. Min Act: -0.1700
Data Index: 8276451 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5962. Min Range: -8.5962
Max Act: 8.2837. Min Act: -0.1700
Data Index: 8363642 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5962. Min Range: -8.5962
Max Act: 8.2212. Min Act: -0.1700
Data Index: 8380624 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5962. Min Range: -8.5962
Max Act: 8.2212. Min Act: -0.1700
Data Index: 6909988 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5962. Min Range: -8.5962
Max Act: 8.2212. Min Act: -0.1700
Data Index: 7184963 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5962. Min Range: -8.5962
Max Act: 8.1587. Min Act: -0.1700
Data Index: 7578423 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5962. Min Range: -8.5962
Max Act: 8.0962. Min Act: -0.1700
Data Index: 43 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5962. Min Range: -8.5962
Max Act: 8.0962. Min Act: -0.1700
Data Index: 4943156 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5962. Min Range: -8.5962
Max Act: 8.0962. Min Act: -0.1700
Data Index: 8818819 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5962. Min Range: -8.5962
Max Act: 8.0337. Min Act: -0.1700
Data Index: 2857666 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5962. Min Range: -8.5962
Max Act: 8.0024. Min Act: -0.1700
Data Index: 2195647 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5962. Min Range: -8.5962
Max Act: 8.0024. Min Act: -0.1700
Data Index: 5666982 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5962. Min Range: -8.5962
Max Act: 7.9712. Min Act: -0.1700
Data Index: 3090802 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5962. Min Range: -8.5962
Max Act: 7.9399. Min Act: -0.1700
Data Index: 4304719 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5962. Min Range: -8.5962
Max Act: 7.9399. Min Act: -0.1700
Data Index: 85005 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5962. Min Range: -8.5962
Max Act: 7.9712. Min Act: -0.1700
Data Index: 4979790 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #19