Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3372 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7532. Min Range: -8.7532
Max Act: 8.7532. Min Act: -0.1700
Data Index: 7637474 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7532. Min Range: -8.7532
Max Act: 8.1907. Min Act: -0.1700
Data Index: 2209843 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7532. Min Range: -8.7532
Max Act: 8.0032. Min Act: -0.1700
Data Index: 595644 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7532. Min Range: -8.7532
Max Act: 8.0032. Min Act: -0.1700
Data Index: 5890625 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7532. Min Range: -8.7532
Max Act: 7.9407. Min Act: -0.1700
Data Index: 3042680 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7532. Min Range: -8.7532
Max Act: 7.9407. Min Act: -0.1700
Data Index: 7441109 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7532. Min Range: -8.7532
Max Act: 7.9407. Min Act: -0.1700
Data Index: 129355 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7532. Min Range: -8.7532
Max Act: 7.9407. Min Act: -0.1700
Data Index: 5372770 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7532. Min Range: -8.7532
Max Act: 7.9407. Min Act: -0.1700
Data Index: 8126864 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7532. Min Range: -8.7532
Max Act: 7.9407. Min Act: -0.1700
Data Index: 6433795 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7532. Min Range: -8.7532
Max Act: 7.8782. Min Act: -0.1700
Data Index: 3347953 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7532. Min Range: -8.7532
Max Act: 7.8157. Min Act: -0.1700
Data Index: 1064876 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7532. Min Range: -8.7532
Max Act: 7.8157. Min Act: -0.1700
Data Index: 415603 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7532. Min Range: -8.7532
Max Act: 7.8157. Min Act: -0.1700
Data Index: 5067162 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7532. Min Range: -8.7532
Max Act: 7.8157. Min Act: -0.1700
Data Index: 8746526 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7532. Min Range: -8.7532
Max Act: 7.7532. Min Act: -0.1700
Data Index: 3552411 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7532. Min Range: -8.7532
Max Act: 7.7532. Min Act: -0.1700
Data Index: 6093072 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7532. Min Range: -8.7532
Max Act: 7.7532. Min Act: -0.1700
Data Index: 2628580 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7532. Min Range: -8.7532
Max Act: 7.7532. Min Act: -0.1700
Data Index: 7937146 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7532. Min Range: -8.7532
Max Act: 7.7532. Min Act: -0.1700
Data Index: 7499118 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #19