Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3104 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3087. Min Range: -7.3087
Max Act: 7.3087. Min Act: -0.1700
Data Index: 8172677 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3087. Min Range: -7.3087
Max Act: 7.2462. Min Act: -0.1700
Data Index: 6561962 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3087. Min Range: -7.3087
Max Act: 7.1524. Min Act: -0.1700
Data Index: 6805098 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3087. Min Range: -7.3087
Max Act: 7.1524. Min Act: -0.1700
Data Index: 2592113 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3087. Min Range: -7.3087
Max Act: 7.0587. Min Act: -0.1700
Data Index: 425753 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3087. Min Range: -7.3087
Max Act: 7.0274. Min Act: -0.1700
Data Index: 3199640 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3087. Min Range: -7.3087
Max Act: 6.9649. Min Act: -0.1700
Data Index: 6332742 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3087. Min Range: -7.3087
Max Act: 6.9024. Min Act: -0.1700
Data Index: 5287410 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3087. Min Range: -7.3087
Max Act: 6.9024. Min Act: -0.1700
Data Index: 3301779 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3087. Min Range: -7.3087
Max Act: 6.8399. Min Act: -0.1700
Data Index: 648923 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3087. Min Range: -7.3087
Max Act: 6.8087. Min Act: -0.1700
Data Index: 710632 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3087. Min Range: -7.3087
Max Act: 6.8087. Min Act: -0.1700
Data Index: 115391 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3087. Min Range: -7.3087
Max Act: 6.8087. Min Act: -0.1700
Data Index: 7497559 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3087. Min Range: -7.3087
Max Act: 6.7149. Min Act: -0.1700
Data Index: 4644912 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3087. Min Range: -7.3087
Max Act: 6.7462. Min Act: -0.1700
Data Index: 5027741 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3087. Min Range: -7.3087
Max Act: 6.7149. Min Act: -0.1700
Data Index: 1184472 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3087. Min Range: -7.3087
Max Act: 6.7462. Min Act: -0.1700
Data Index: 16968 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3087. Min Range: -7.3087
Max Act: 6.6837. Min Act: -0.1700
Data Index: 6805097 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3087. Min Range: -7.3087
Max Act: 6.6524. Min Act: -0.1700
Data Index: 3153452 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3087. Min Range: -7.3087
Max Act: 6.6524. Min Act: -0.1700
Data Index: 2787652 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #19