Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3647 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1907. Min Range: -6.1907
Max Act: 6.1907. Min Act: -0.1700
Data Index: 8604318 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1907. Min Range: -6.1907
Max Act: 6.1595. Min Act: -0.1700
Data Index: 2848055 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1907. Min Range: -6.1907
Max Act: 6.1595. Min Act: -0.1700
Data Index: 3838506 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1907. Min Range: -6.1907
Max Act: 6.0657. Min Act: -0.1700
Data Index: 2926199 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1907. Min Range: -6.1907
Max Act: 6.0345. Min Act: -0.1700
Data Index: 8820831 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1907. Min Range: -6.1907
Max Act: 6.0032. Min Act: -0.1700
Data Index: 8387571 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1907. Min Range: -6.1907
Max Act: 5.9095. Min Act: -0.1700
Data Index: 3395246 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1907. Min Range: -6.1907
Max Act: 5.8157. Min Act: -0.1700
Data Index: 4244768 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1907. Min Range: -6.1907
Max Act: 5.7845. Min Act: -0.1700
Data Index: 5297754 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1907. Min Range: -6.1907
Max Act: 5.7845. Min Act: -0.1700
Data Index: 8197870 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1907. Min Range: -6.1907
Max Act: 5.7532. Min Act: -0.1700
Data Index: 5166974 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1907. Min Range: -6.1907
Max Act: 5.7220. Min Act: -0.1700
Data Index: 8679050 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1907. Min Range: -6.1907
Max Act: 5.7220. Min Act: -0.1700
Data Index: 1357918 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1907. Min Range: -6.1907
Max Act: 5.7220. Min Act: -0.1700
Data Index: 6412112 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1907. Min Range: -6.1907
Max Act: 5.7220. Min Act: -0.1700
Data Index: 4784769 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1907. Min Range: -6.1907
Max Act: 5.7220. Min Act: -0.1700
Data Index: 8359123 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1907. Min Range: -6.1907
Max Act: 5.7220. Min Act: -0.1700
Data Index: 1265750 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1907. Min Range: -6.1907
Max Act: 5.6907. Min Act: -0.1700
Data Index: 2378199 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1907. Min Range: -6.1907
Max Act: 5.7220. Min Act: -0.1700
Data Index: 2388212 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1907. Min Range: -6.1907
Max Act: 5.7220. Min Act: -0.1700
Data Index: 3211979 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #19